locate-steer-and-improve-a-practical-survey-of

【数据与研究】Mechanistic Interpretability (MI) has emerged as a vital approach to demystify the opaque decision-making of Large Language Models (LLMs). However, existing reviews primarily treat MI as an observational science, summarizing analytical insights while lacking a systematic framework for actionable intervention. To bridge this gap, we present a practica…

独立 GitHub 快照 · 自动分类 · 以原作者文档为准