Spectral Principal Paths: A Spectral Perspective on Linear Representation Formation in LLMs 事件

Spectral Principal Paths: A Spectral Perspective on Linear Representation Formation in LLMs arXiv:2506.08543v3 Announce Type: replace Abstract: High-level representations have become a central focus in enhancing AI transparency and control, shifting attention from individual neurons or circuits to structured semantic directions that align with human-interpretable concepts. While the Linear Representation Hypothesis (LRH) suggests that such directions emerge in representations, it remains unclea