AI safety researcher. Interested in understanding the principles behind LLM learning / generalization
Highlights
- Pro
Pinned Loading
-
inoculation-prompting/inoculation-prompting
inoculation-prompting/inoculation-prompting PublicOfficial codebase for Inoculation Prompting
-
emergent-misalignment/emergent-misalignment
emergent-misalignment/emergent-misalignment Public -
steering-bench
steering-bench PublicOfficial codebase for "Analyzing the Generalization and Reliability of Steering Vectors"
Something went wrong, please refresh the page to try again.
If the problem persists, check the GitHub status page or contact support.
If the problem persists, check the GitHub status page or contact support.





