The Answer-Basin Representation Hypothesis: We Are Not Probing or Steering Concepts
Linear probing and activation steering use linear directions to predict and control behavior-level concepts such as correctness, safety, and social bias in question answering. We call these \emph{behavior-level concept directions}. Drawing on the Linear Representation Hypothesis (LRH) and circuit studies, these directions are often interpreted as concept representations. Yet controlled evidence for linear concept structure and local mechanisms does not establish that these directions represent the intended behavioral concepts, leaving probing and steering without a unified theoretical account. We propose the \emph{Answer-Basin Representation Hypothesis} (ABRH): the model's own answer meas...
| Authors | Manjiang Yu, Hongji Li, Zihan Wang et al. |
|---|---|
| Primary category | cs.CL |
| Published | 21 September 2026 |
| Last updated at source | 2 October 2026 |
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.