Where Steering Signals Come From: Activation Source Selection in Activation Steering

[2607.25270] Where Steering Signals Come From: Activation Source Selection in Activation Steering Skip to main content Search Submit Donate Log in Computer Science > Computation and Language arXiv:2607.25270 (cs) [Submitted on 28 Jul 2026 ( v1 ), last revised 28 Aug 2026 (this version, v2)] Title: Where Steering Signals Come From: Activation Source Selection in Activation Steering Authors: Jiaran Ye , Lingxu Ran , Zijun Yao , Chenpeng Wang , Yong Jiang , Lei Hou , Juanzi Li , Liangming Pan View PDF HTML (experimental) Abstract: Activation steering controls language models by adding vectors or features to hidden states at inference time, but the upstream source of these steering signals is often treated as a secondary detail. We study this source choice as activation source selection: the combination of source context and activation readout policy used to collect the hidden states from which a steering signal is built. Holding the downstream intervention fixed, we show across three instruction-tuned models and four steering task families that changing only the source activations substantially changes steering success. We further find that effective steering is not explained simply by whether the desired behavior appears in the source text. Instead, strong signals come from execution-boundary states, where the model is about to produce or continue the target behavior. This pre-/post-realization distinction explains why answer-based sources sometimes work: their useful component aligns with execution-boundary directions rather than target appearance alone. Building on this view, we introduce tail subtraction, which removes shared prompt and continuation semantics from boundary states and yields cleaner, more stable steering signals. Overall, our results suggest that steering depends on representations of what the model is about to do, not merely on what has already appeared. Comments: Accepted to Findings of EMNLP 2026 Subjects: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI); Machine Learning (cs.LG) Cite as: arXiv:2607.25270 [cs.CL] (or arXiv:2607.25270v2 [cs.CL] for this version) https://doi.org/10.48550/arXiv.2607.25270 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Jiaran Ye [ view email ] [v1] Tue, 28 Jul 2026 04:18:24 UTC (301 KB) [v2] Fri, 28 Aug 2026 10:50:13 UTC (297 KB) Full-text links: Access Paper: View PDF HTML (experimental) TeX Source view license Additional Features Audio Summary Current browse context: cs.CL < prev | next > new | recent | 2026-07 Change to browse by: cs cs.AI cs.LG References & Citations SciX Google Scholar Semantic Scholar export BibTeX citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab)

Related documents

• Where Steering Signals Come From: Activation Source Selection in Activation Steering#682780
• Subliminal Steering: Stronger Encoding of Hidden Signals#614999
• Subliminal Steering: Stronger Encoding of Hidden Signals#614032
• Coordinated acetylcholine release and adaptation of neuronal representations in the retrosplenial cortex during contextual uncertainty#259211
• Vault: One-Step Latent Generation with Positive-Anchored Rewards for Autonomous Driving#1118594