{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,6]],"date-time":"2026-09-06T17:08:58Z","timestamp":1788714538794,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":38,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032376756","type":"print"},{"value":"9783032376763","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,9,7]],"date-time":"2026-09-07T00:00:00Z","timestamp":1788739200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,9,7]],"date-time":"2026-09-07T00:00:00Z","timestamp":1788739200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2027]]},"DOI":"10.1007\/978-3-032-37676-3_11","type":"book-chapter","created":{"date-parts":[[2026,9,6]],"date-time":"2026-09-06T16:12:58Z","timestamp":1788711178000},"page":"180-195","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["SAIF: A Sparse Autoencoder Framework for\u00a0Interpreting and\u00a0Steering Instruction Following of\u00a0Language Models"],"prefix":"10.1007","author":[{"given":"Zirui","family":"He","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haiyan","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yiran","family":"Qiao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fan","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ali","family":"Payani","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jing","family":"Ma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mengnan","family":"Du","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,7]]},"reference":[{"issue":"1","key":"11_CR1","doi-asserted-by":"publisher","first-page":"207","DOI":"10.1162\/coli_a_00422","volume":"48","author":"Y Belinkov","year":"2022","unstructured":"Belinkov, Y.: Probing classifiers: promises, shortcomings, and advances. Comput. Linguist. 48(1), 207\u2013219 (2022)","journal-title":"Comput. Linguist."},{"key":"11_CR2","unstructured":"Bricken, T., et\u00a0al.: Towards monosemanticity: decomposing language models with dictionary learning (2023). https:\/\/transformer-circuits.pub\/2023\/monosemantic-features\/index.html"},{"key":"11_CR3","unstructured":"Chalnev, S., Siu, M., Conmy, A.: Improving steering vectors by targeting sparse autoencoder features. arXiv preprint: arXiv:2411.02193 (2024)"},{"key":"11_CR4","unstructured":"Chung, H.W., et\u00a0al.: Scaling instruction-finetuned language models. J. Mach. Learn. Res. (JMLR) 25(70), 1\u201353 (2024). http:\/\/jmlr.org\/papers\/v25\/23-0870.html"},{"key":"11_CR5","doi-asserted-by":"crossref","unstructured":"Conneau, A., et al.: XNLI: evaluating cross-lingual sentence representations. In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics (2018)","DOI":"10.18653\/v1\/D18-1269"},{"key":"11_CR6","unstructured":"Ferrando, J., Obeso, O.B., Rajamanoharan, S., Nanda, N.: Do i know this entity? Knowledge awareness and hallucinations in language models. In: The Thirteenth International Conference on Learning Representations (2025). https:\/\/openreview.net\/forum?id=WCRQFlji2q"},{"key":"11_CR7","doi-asserted-by":"crossref","unstructured":"Gallifant, J., Chen, S., Sasse, K., Aerts, H., Hartvigsen, T., Bitterman, D.S.: Sparse autoencoder features for classifications and transferability. arXiv preprint: arXiv:2502.11367 (2025)","DOI":"10.18653\/v1\/2025.emnlp-main.1521"},{"key":"11_CR8","unstructured":"Gao, L., et al.: Scaling and evaluating sparse autoencoders. arXiv preprint: arXiv:2406.04093 (2024)"},{"key":"11_CR9","unstructured":"He, Z., et al.: Llama scope: extracting millions of features from llama-3.1-8b with sparse autoencoders. arXiv preprint: arXiv:2410.20526 (2024)"},{"key":"11_CR10","unstructured":"Hewitt, J., Liu, N.F., Liang, P., Manning, C.D.: Instruction following without instruction tuning. arXiv preprint: arXiv:2409.14254 (2024)"},{"key":"11_CR11","unstructured":"Jin, M., Yu, Q., Huang, J., Zeng, Q., Wang, Z., Hua, W., et\u00a0al.: Exploring concept depth: how large language models acquire knowledge and concept at different layers? In: Rambow, O., Wanner, L., Apidianaki, M., Al-Khalifa, H., Eugenio, B.D., Schockaert, S. (eds.) Proceedings of the 31st International Conference on Computational Linguistics, pp. 558\u2013573. Association for Computational Linguistics, Abu Dhabi (2025). https:\/\/aclanthology.org\/2025.coling-main.37\/"},{"key":"11_CR12","doi-asserted-by":"publisher","unstructured":"Jin, M., et al.: The impact of reasoning step length on large language models. In: Ku, L.W., Martins, A., Srikumar, V. (eds.) Findings of the Association for Computational Linguistics: ACL 2024, pp. 1830\u20131842. Association for Computational Linguistics, Bangkok (2024). https:\/\/doi.org\/10.18653\/v1\/2024.findings-acl.108","DOI":"10.18653\/v1\/2024.findings-acl.108"},{"key":"11_CR13","unstructured":"Jorgensen, O., Cope, D., Schoots, N., Shanahan, M.: Improving activation steering in language models with mean-centring. In: Responsible Language Models Workshop at AAAI-24 (2024)"},{"key":"11_CR14","unstructured":"Kim, B., Wattenberg, M., Gilmer, J., Cai, C., Wexler, J., Viegas, F.: Interpretability beyond feature attribution: Quantitative testing with concept activation vectors (TCAV). In: International Conference on Machine Learning, pp. 2668\u20132677. PMLR (2018)"},{"key":"11_CR15","unstructured":"Kissane, C., Krzyzanowski, R., Bloom, J.I., Conmy, A., Nanda, N.: Interpreting attention layer outputs with sparse autoencoders. In: ICML 2024 Workshop on Mechanistic Interpretability (2024)"},{"key":"11_CR16","doi-asserted-by":"crossref","unstructured":"Kung, P.N., Peng, N.: Do models really learn to follow instructions? An empirical study of instruction tuning. In: Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pp. 1317\u20131328 (2023)","DOI":"10.18653\/v1\/2023.acl-short.113"},{"key":"11_CR17","unstructured":"Li, K., Liu, T., Bashkansky, N., Bau, D., Vi\u00e9gas, F., Pfister, H., Wattenberg, M.: Measuring and controlling persona drift in language model dialogs. arXiv preprint: arXiv:2402.10962 (2024)"},{"key":"11_CR18","doi-asserted-by":"crossref","unstructured":"Li, K., Patel, O., Vi\u00e9gas, F., Pfister, H., Wattenberg, M.: Inference-time intervention: eliciting truthful answers from a language model. In: Advances in Neural Information Processing Systems, vol. 36 (2024)","DOI":"10.52202\/075280-1797"},{"key":"11_CR19","doi-asserted-by":"crossref","unstructured":"Lieberum, T., et al.: Gemma scope: open sparse autoencoders everywhere all at once on Gemma 2. arXiv preprint: arXiv:2408.05147 (2024)","DOI":"10.18653\/v1\/2024.blackboxnlp-1.19"},{"key":"11_CR20","unstructured":"Lin, J.: Neuronpedia: interactive reference and tooling for analyzing neural networks (2023). https:\/\/www.neuronpedia.org. software available from neuronpedia.org"},{"key":"11_CR21","doi-asserted-by":"crossref","unstructured":"Liu, Y., Zeng, X., Meng, F., Zhou, J.: Instruction position matters in sequence generation with large language models. In: Findings of the Association for Computational Linguistics: ACL 2024 (2024)","DOI":"10.18653\/v1\/2024.findings-acl.693"},{"key":"11_CR22","doi-asserted-by":"publisher","unstructured":"Ma, W., Yang, C., K\u00e4stner, C.: (why) is my prompt getting worse? Rethinking regression testing for evolving LLM APIs. In: Proceedings of the IEEE\/ACM 3rd International Conference on AI Engineering - Software Engineering for AI, CAIN \u201924, pp. 166\u2013171. Association for Computing Machinery, New York (2024). https:\/\/doi.org\/10.1145\/3644815.3644950","DOI":"10.1145\/3644815.3644950"},{"key":"11_CR23","doi-asserted-by":"publisher","unstructured":"Olshausen, B.A., Field, D.J.: Sparse coding with an overcomplete basis set: a strategy employed by V1? Vis. Res. 37(23), 3311\u20133325 (1997). https:\/\/doi.org\/10.1016\/S0042-6989(97)00169-7","DOI":"10.1016\/S0042-6989(97)00169-7"},{"key":"11_CR24","doi-asserted-by":"crossref","unstructured":"Ouyang, L., et al.: Training language models to follow instructions with human feedback. In: Advances in Neural Information Processing Systems (NeurIPS), vol. 35, pp. 27730\u201327744 (2022)","DOI":"10.52202\/068431-2011"},{"key":"11_CR25","unstructured":"Rajamanoharan, S., et al.: Jumping ahead: improving reconstruction fidelity with JumpReLU sparse autoencoders (2024). https:\/\/arxiv.org\/abs\/2407.14435"},{"key":"11_CR26","doi-asserted-by":"crossref","unstructured":"Rimsky, N., Gabrieli, N., Schulz, J., Tong, M., Hubinger, E., Turner, A.: Steering llama 2 via contrastive activation addition. In: Ku, L.W., Martins, A., Srikumar, V. (eds.) Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) (2024)","DOI":"10.18653\/v1\/2024.acl-long.828"},{"key":"11_CR27","unstructured":"Sanh, V., et al.: Multitask prompted training enables zero-shot task generalization. In: International Conference on Learning Representations (2022)"},{"key":"11_CR28","unstructured":"Sharkey, L., Braun, D., Millidge, B.: Taking features out of superposition with sparse autoencoders (2022). https:\/\/www.alignmentforum.org\/posts\/z6QQJbtpkEAX3Aojj\/inter im-research-report-taking-features-out-of-superposition"},{"key":"11_CR29","doi-asserted-by":"crossref","unstructured":"Stolfo, A., Balachandran, V., Yousefi, S., Horvitz, E., Nushi, B.: Improving instruction-following in language models through activation steering. arXiv preprint: arXiv:2410.12877 (2024)","DOI":"10.32388\/BTHT4K"},{"key":"11_CR30","doi-asserted-by":"publisher","unstructured":"Sun, J., et al.: Evaluating large language models on controlled generation tasks. In: Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 3155\u20133168. Association for Computational Linguistics, Singapore (2023). https:\/\/doi.org\/10.18653\/v1\/2023.emnlp-main.190","DOI":"10.18653\/v1\/2023.emnlp-main.190"},{"key":"11_CR31","unstructured":"Team, G., et al.: Gemma 2: improving open language models at a practical size. arXiv preprint: arXiv:2408.00118 (2024)"},{"key":"11_CR32","unstructured":"Tigges, C., Hollinsworth, O.J., Geiger, A., Nanda, N.: Linear representations of sentiment in large language models (2023). https:\/\/arxiv.org\/abs\/2310.15154"},{"key":"11_CR33","unstructured":"Wei, J., et al.: Finetuned language models are zero-shot learners. In: International Conference on Learning Representations (ICLR) (2022). https:\/\/openreview.net\/forum?id=gEZrGCozdqR"},{"key":"11_CR34","unstructured":"Wu, X., Yuan, J., Yao, W., Zhai, X., Liu, N.: Interpreting and steering LLMs with mutual information-based explanations on sparse autoencoders. arXiv preprint: arXiv:2502.15576 (2025)"},{"key":"11_CR35","unstructured":"Zhao, H., Zhao, H., Shen, B., Payani, A., Yang, F., Du, M.: Beyond single concept vector: modeling concept subspace in LLMs with gaussian distribution. In: The Thirteenth International Conference on Learning Representations (2025), https:\/\/openreview.net\/forum?id=CvttyK4XzV"},{"key":"11_CR36","doi-asserted-by":"crossref","unstructured":"Zhou, C., et\u00a0al.: LIMA: less is more for alignment. In: Advances in Neural Information Processing Systems, vol. 36 (2024)","DOI":"10.52202\/075280-2400"},{"key":"11_CR37","unstructured":"Zhou, J., et al.: Instruction-following evaluation for large language models. arXiv preprint: arXiv:2311.07911 (2023)"},{"key":"11_CR38","unstructured":"Zou, A., Phan, L., Chen, S., Campbell, J., Guo, P., Ren, R., et\u00a0al.: Representation engineering: a top-down approach to ai transparency (2023). https:\/\/arxiv.org\/abs\/2310.01405"}],"container-title":["Lecture Notes in Computer Science","Machine Learning and Knowledge Discovery in Databases. Research Track"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-37676-3_11","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,6]],"date-time":"2026-09-06T16:13:07Z","timestamp":1788711187000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37676-3_11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,7]]},"ISBN":["9783032376756","9783032376763"],"references-count":38,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37676-3_11","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,7]]},"assertion":[{"value":"7 September 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECML PKDD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Joint European Conference on Machine Learning and Knowledge Discovery in Databases","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Naples","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7 September 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11 September 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecml2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ecmlpkdd.org\/2026\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}