When Models Refuse: Political Steerability and Feature Richness as Measures of Ideological Depth

ArXi:2508.21448v3 Announce Type: replace Large language models (LLMs) sometimes refuse to follow benign instructions, such as declining to argue a political position or adopt a stated persona, and such refusals are commonly read as safety guardrails at work. We ask whether they can instead signal a **capability deficit**: a shortage of the internal representations a model needs to reason from the instructed perspective. To investigate, we