Alternatives and similar repositories for sleeper-agents

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

• ckkissane / crosscoder-model-diff-replication
  Open source replication of Anthropic's Crosscoders for Model Diffing
  ☆63Updated last year
• 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…
  ☆28Updated last year
• UFO-101 / auto-circuit
  A library for efficient patching and automatic circuit discovery.
  ☆82Updated 5 months ago
• slavachalnev / SAE-TS
  Improving Steering Vectors by Targeting Sparse Autoencoder Features
  ☆24Updated last year
• ApolloResearch / e2e_sae
  Sparse Autoencoder Training Library
  ☆56Updated 7 months ago
• METR / RE-Bench
  ☆124Updated 2 months ago
• FlyingPumba / InterpBench
  A benchmark for mechanistic discovery of circuits in Transformers
  ☆16Updated last year
• ArthurConmy / Automatic-Circuit-Discovery
  ☆260Updated last year
• redwoodresearch / interp
  Redwood Research's transformer interpretability tools
  ☆14Updated 3 years ago
• science-of-finetuning / diffing-toolkit
  A toolkit that provides a range of model diffing techniques including a UI to visualize them interactively.
  ☆43Updated this week
• UKGovernmentBEIS / control-arena
  ControlArena is a collection of settings, model organisms and protocols - for running control experiments.
  ☆135Updated last week
• METR / task-standard
  METR Task Standard
  ☆169Updated 10 months ago
• TransformerLensOrg / CircuitsVis
  Mechanistic Interpretability Visualizations using React
  ☆303Updated last year
• redwoodresearch / alignment_faking_public
  ☆82Updated 2 months ago
• annahdo / implementing_activation_steering
  A collection of different ways to implement accessing and modifying internal model activations for LLMs
  ☆19Updated last year
• steering-vectors / steering-vectors
  Steering vectors for transformer language models in Pytorch / Huggingface
  ☆134Updated 10 months ago
• nrimsky / CAA
  Steering Llama 2 with Contrastive Activation Addition
  ☆201Updated last year
• KoyenaPal / future-lens
  Code and Data Repo for the CoNLL Paper -- Future Lens: Anticipating Subsequent Tokens from a Single Hidden State
  ☆20Updated last month
• neelnanda-io / Crosscoders
  ☆58Updated last year
• safety-research / safety-tooling
  Inference API for many LLMs and other useful tools for empirical research
  ☆84Updated last week
• callummcdougall / sae_visualizer
  ☆29Updated last year
• explanare / ravel
  Evaluate interpretability methods on localizing and disentangling concepts in LLMs.
  ☆57Updated last month
• EleutherAI / delphi
  Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …
  ☆234Updated last week
• curt-tigges / probity
  ☆19Updated 8 months ago
• amack315 / unsupervised-steering-vectors
  ☆36Updated last year
• neelnanda-io / 1L-Sparse-Autoencoder
  ☆132Updated 2 years ago
• LoryPack / LLM-LieDetector
  Code for the ICLR 2024 paper "How to catch an AI liar: Lie detection in black-box LLMs by asking unrelated questions"
  ☆71Updated last year
• Butanium / nnterp
  Unified access to Large Language Model modules using NNsight
  ☆70Updated last month
• jbloomAus / SAEDashboard
  ☆82Updated this week
• stanfordnlp / axbench
  Stanford NLP Python library for benchmarking the utility of LLM interpretability methods
  ☆154Updated 5 months ago