Mapping the mind of a large language model

This post details the successful application of dictionary learning to Claude 3.0 Sonnet to extract millions of features representing concepts. It describes the engineering challenges of scaling this technique and the scientific validation through feature manipulation. Key contributions include identifying features for concrete entities (cities, people), abstract concepts (inner conflict, bugs), and safety-relevant capabilities (misuse potential, bias, sycophancy). The post demonstrates that these features are causally linked to model behavior, enabling manipulation to alter responses, and validates their role in internal reasoning and safety. It also highlights the computational cost of this approach and the ongoing need to understand feature circuits.