Activation Oracles are LLMs trained to read activation snapshots and answer natural-language questions, generalizing to misalignment audits and secret-elicitation tasks.

We study behavioral self-awareness -- an LLM's ability to articulate its behaviors without requiring in-context examples.

Humans acquire knowledge by observing the external world, but also by introspection. Can LLMs introspect?

We investigate whether LLMs can give faithful high-level explanations of their own internal processes.