Alternatives and similar repositories for sleeper-agents:

Users that are interested in sleeper-agents are comparing it to the libraries listed below

• UKGovernmentBEIS / control-arena
  ControlArena is a suite of realistic settings, mimicking complex deployment environments, for running control evaluations. This is an alp…
  ☆54Updated this week
• slavachalnev / SAE-TS
  Improving Steering Vectors by Targeting Sparse Autoencoder Features
  ☆19Updated 5 months ago
• ArthurConmy / Automatic-Circuit-Discovery
  ☆223Updated 7 months ago
• METR / task-standard
  METR Task Standard
  ☆146Updated 3 months ago
• LRudL / evalugator
  (Model-written) LLM evals library
  ☆18Updated 4 months ago
• longtermrisk / openweights
  A python sdk for LLM finetuning and inference on runpod infrastructure
  ☆11Updated this week
• TransformerLensOrg / CircuitsVis
  Mechanistic Interpretability Visualizations using React
  ☆242Updated 4 months ago
• ckkissane / crosscoder-model-diff-replication
  Open source replication of Anthropic's Crosscoders for Model Diffing
  ☆55Updated 6 months ago
• adamkarvonen / SAEBench
  ☆93Updated 3 weeks ago
• steering-vectors / steering-vectors
  Steering vectors for transformer language models in Pytorch / Huggingface
  ☆99Updated 2 months ago
• annahdo / implementing_activation_steering
  A collection of different ways to implement accessing and modifying internal model activations for LLMs
  ☆15Updated 6 months ago
• safety-research / safety-tooling
  Inference API for many LLMs and other useful tools for empirical research
  ☆40Updated last week
• callummcdougall / sae_visualizer
  ☆27Updated last year
• redwoodresearch / alignment_faking_public
  ☆54Updated 3 months ago
• neelnanda-io / 1L-Sparse-Autoencoder
  ☆121Updated last year
• amack315 / unsupervised-steering-vectors
  ☆31Updated last year
• curt-tigges / probity
  ☆12Updated 3 weeks ago
• UFO-101 / auto-circuit
  A library for efficient patching and automatic circuit discovery.
  ☆64Updated 2 weeks ago
• neelnanda-io / Crosscoders
  ☆40Updated 5 months ago
• nrimsky / LM-exp
  LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces
  ☆91Updated last year
• EleutherAI / delphi
  Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …
  ☆172Updated this week
• ApolloResearch / sample
  Repository with sample code using Apollo's suggested engineering practices
  ☆8Updated 4 months ago
• saprmarks / feature-circuits
  ☆165Updated last month
• callummcdougall / ARENA_2.0
  Resources for skilling up in AI alignment research engineering. Covers basics of deep learning, mechanistic interpretability, and RL.
  ☆211Updated last year
• redwoodresearch / interp
  Redwood Research's transformer interpretability tools
  ☆14Updated 3 years ago
• KoyenaPal / future-lens
  Code and Data Repo for the CoNLL Paper -- Future Lens: Anticipating Subsequent Tokens from a Single Hidden State
  ☆18Updated last year
• redwoodresearch / mlab
  Machine Learning for Alignment Bootcamp
  ☆72Updated 3 years ago
• timaeus-research / devinterp
  Tools for studying developmental interpretability in neural networks.
  ☆89Updated 3 months ago
• alan-cooney / transformer-from-scratch
  Decoder only transformer, built from scratch with PyTorch
  ☆28Updated last year
• AsaCooperStickland / situational-awareness-evals
  Measuring the situational awareness of language models
  ☆34Updated last year