How Do Linear Probes Emerge? A Circuit-Tracing Framework with Concept-Targeted Attribution

[2608.27510] How Do Linear Probes Emerge? A Circuit-Tracing Framework with Concept-Targeted Attribution Skip to main content Search Submit Donate Log in Computer Science > Computation and Language arXiv:2608.27510 (cs) [Submitted on 27 Aug 2026] Title: How Do Linear Probes Emerge? A Circuit-Tracing Framework with Concept-Targeted Attribution Authors: Vedant Palit , Florent Draye , Terry Jingchen Zhang , Bernhard Schölkopf , Zhijing Jin View PDF HTML (experimental) Abstract: Transcoder attribution graphs are usually trained to explain why a model assigns high probability to a particular next token. We introduce Concept-Targeted Attribution (CTA), which instead trains attribution graphs with respect to a linear probe direction. CTA therefore yields probe-specific circuits that explain why an internal concept representation arises in a prompt, independently of whether it is expressed in the generated token. Using Cross-Layer Transcoders, we show that these probe-targeted graphs contain predictive structure: graph-level features predict probe accuracy across four widely studied concept categories ($\rho = 0.91$, $R^2 = 0.84$), while local features identify the sparse components driving per-prompt classification. This connects probe performance to interpretable circuit structure, allowing us to ask not only whether a probe works, but which internal computations make it work. Causal ablations further show that probe-targeted and logit-targeted graphs capture functionally distinct mechanisms. Removing probe-relevant features reduces internal concept scores while largely preserving generated tokens, whereas removing logit-relevant features changes the generated token in 92% to 100% of cases with near-zero effect on probe scores. CTA provides a framework for moving from behavioral probe accuracy to mechanistic explanations of probe performance, enabling more detailed audits of internal concept representations, including safety-critical ones. Our code is available at this https URL Comments: Accepted to EMNLP 2026 (Main Conference). 29 pages, 18 figures, 9 tables Subjects: Computation and Language (cs.CL) ; Machine Learning (cs.LG) Cite as: arXiv:2608.27510 [cs.CL] (or arXiv:2608.27510v1 [cs.CL] for this version) https://doi.org/10.48550/arXiv.2608.27510 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Zhijing Jin [ view email ] [v1] Thu, 27 Aug 2026 08:12:49 UTC (1,632 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 | 2026-08 Change to browse by: cs 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

• How Do Linear Probes Emerge? A Circuit-Tracing Framework with Concept-Targeted Attribution#779448
• Data Attribution via Sketched Metadifferentiation#1149454
• Representational Simplicity and Circuit Size Dissociate in a Threshold-Dependent Way: A Controlled Test via Adversarial Training#1130732
• Tracing Stereotypes from Representation to Output in Multilingual LLMs#985686
• Testable or bust: theoretical lessons for predictive processing#732883