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…
  ☆60Updated this week
• LRudL / evalugator
  (Model-written) LLM evals library
  ☆18Updated 5 months ago
• longtermrisk / openweights
  A python sdk for LLM finetuning and inference on runpod infrastructure
  ☆11Updated last week
• slavachalnev / SAE-TS
  Improving Steering Vectors by Targeting Sparse Autoencoder Features
  ☆20Updated 6 months ago
• callummcdougall / sae_visualizer
  ☆28Updated last year
• redwoodresearch / alignment_faking_public
  ☆62Updated last week
• ckkissane / crosscoder-model-diff-replication
  Open source replication of Anthropic's Crosscoders for Model Diffing
  ☆55Updated 7 months ago
• annahdo / implementing_activation_steering
  A collection of different ways to implement accessing and modifying internal model activations for LLMs
  ☆16Updated 7 months ago
• METR / task-standard
  METR Task Standard
  ☆147Updated 4 months ago
• ApolloResearch / sample
  Repository with sample code using Apollo's suggested engineering practices
  ☆9Updated 5 months ago
• amack315 / unsupervised-steering-vectors
  ☆31Updated last year
• neelnanda-io / Crosscoders
  ☆43Updated 6 months ago
• steering-vectors / steering-vectors
  Steering vectors for transformer language models in Pytorch / Huggingface
  ☆101Updated 3 months ago
• neelnanda-io / 1L-Sparse-Autoencoder
  ☆121Updated last year
• UFO-101 / auto-circuit
  A library for efficient patching and automatic circuit discovery.
  ☆65Updated last month
• TransformerLensOrg / CircuitsVis
  Mechanistic Interpretability Visualizations using React
  ☆251Updated 5 months ago
• METR / public-tasks
  ☆96Updated 2 months ago
• ArthurConmy / Automatic-Circuit-Discovery
  ☆223Updated 8 months ago
• nrimsky / LM-exp
  LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces
  ☆93Updated last year
• redwoodresearch / interp
  Redwood Research's transformer interpretability tools
  ☆15Updated 3 years ago
• METR / RE-Bench
  ☆76Updated last month
• safety-research / safety-tooling
  Inference API for many LLMs and other useful tools for empirical research
  ☆47Updated last week
• alan-cooney / transformer-from-scratch
  Decoder only transformer, built from scratch with PyTorch
  ☆30Updated last year
• jkminder / dictionary_learning
  Modified to support crosscoder training.
  ☆17Updated last week
• EleutherAI / elk-generalization
  Investigating the generalization behavior of LM probes trained to predict truth labels: (1) from one annotator to another, and (2) from e…
  ☆26Updated last year
• nrimsky / CAA
  Steering Llama 2 with Contrastive Activation Addition
  ☆154Updated last year
• timaeus-research / devinterp
  Tools for studying developmental interpretability in neural networks.
  ☆90Updated 4 months ago
• safety-research / safety-examples
  ☆15Updated 3 weeks ago
• adamkarvonen / SAEBench
  ☆97Updated last month
• redwoodresearch / mlab
  Machine Learning for Alignment Bootcamp
  ☆72Updated 3 years ago