Safety Research
Popular repositories Loading
-
persona_vectors
persona_vectors PublicPersona Vectors: Monitoring and Controlling Character Traits in Language Models
-
-
-
assistant-axis
assistant-axis PublicThe Assistant Axis is a direction in activation space that captures how "Assistant-like" a model's behavior is. Models can drift away from the Assistant during conversations—sometimes toward bizarr…
-
safety-tooling
safety-tooling PublicInference API for many LLMs and other useful tools for empirical research
Repositories
- agentic-backdoor Public
Official implementation of the paper "Agentic Backdoors via Pretraining Poisoning"
- memory-trap Public
Official code and data for "The Memory Trap: Language Agents Overgeneralize from Benign Interactions"
- aligning-ai-teams Public
- multi-agent-welfare-regard Public
Evaluation environments for the paper, "Welfare-Regard in Multi-Agent Systems".
- subliminal-jlens Public
- viz Public
A data visualization library for AI research: consistent, publication-quality figures with one call per chart
- constitutional-adapters Public
Data, code, and results for "Constitutional adapters" (arXiv:2609.36657)
- jpp_lens Public
Code for blog post `J++ Lens: Jacobian Filtering Enables More Faithful Workspace Lenses`
Top languages
Loading…
Most used topics
Loading…