activation-steering

Open repos and models their makers tagged activation-steering, most starred first. The same for everyone.

AI on my own machineRepo

mirror-bench

Measures whether an LLM's self-reports agree with what its internals show. Injected concepts are perfectly recoverable by probes (AUC 1.000) and absent from the model's verbal report - report-state agreement fails in a graded way. Gemma-3-4B, Jacobian lens, ~3,750 trials.

  • 0
  • Python
  • Apache-2.0
  • 3 mo ago
skulitomTake it
Search GitHub and Hugging Face for activation-steering

Get , open it once and sign in. Then come back here and press the button again.

activation-steering: open source repos and models on Take My Repo