Alternatives and similar repositories for sandbagging:

Users that are interested in sandbagging are comparing it to the libraries listed below

• s-ball-10 / jailbreak_dynamics
  ☆14Updated 10 months ago
• redwoodresearch / alignment_faking_public
  ☆54Updated 3 months ago
• nrimsky / CAA
  Steering Llama 2 with Contrastive Activation Addition
  ☆148Updated 11 months ago
• nrimsky / LM-exp
  LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces
  ☆91Updated last year
• saprmarks / feature-circuits
  ☆165Updated last month
• rishub-tamirisa / tamper-resistance
  [ICLR 2025] Official Repository for "Tamper-Resistant Safeguards for Open-Weight LLMs"
  ☆55Updated 2 months ago
• steering-vectors / steering-vectors
  Steering vectors for transformer language models in Pytorch / Huggingface
  ☆99Updated 2 months ago
• UFO-101 / auto-circuit
  A library for efficient patching and automatic circuit discovery.
  ☆64Updated 2 weeks ago
• IBM / activation-steering
  General-purpose activation steering library
  ☆66Updated this week
• ejones313 / auditing-llms
  ☆54Updated 2 years ago
• LRudL / evalugator
  (Model-written) LLM evals library
  ☆18Updated 4 months ago
• montemac / activation_additions
  Algebraic value editing in pretrained language models
  ☆64Updated last year
• wesg52 / sparse-probing-paper
  Sparse probing paper full code.
  ☆56Updated last year
• milesaturpin / cot-unfaithfulness
  ☆42Updated last year
• jacobdunefsky / transcoder_circuits
  ☆111Updated 5 months ago
• adamkarvonen / SAEBench
  ☆93Updated 3 weeks ago
• paul-rottger / xstest
  Röttger et al. (NAACL 2024): "XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models"
  ☆96Updated 2 months ago
• SchwinnL / circuit-breakers-eval
  Independent robustness evaluation of Improving Alignment and Robustness with Short Circuiting
  ☆16Updated 3 weeks ago
• Jiaxin-Wen / MisleadLM
  Official Code for our paper: "Language Models Learn to Mislead Humans via RLHF""
  ☆14Updated 6 months ago
• centerforaisafety / wmdp
  WMDP is a LLM proxy benchmark for hazardous knowledge in bio, cyber, and chemical security. We also release code for RMU, an unlearning m…
  ☆113Updated last year
• ArthurConmy / Automatic-Circuit-Discovery
  ☆223Updated 7 months ago
• amack315 / unsupervised-steering-vectors
  ☆31Updated 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…
  ☆26Updated 11 months ago
• andyrdt / refusal_direction
  Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".
  ☆215Updated 7 months ago
• ckkissane / crosscoder-model-diff-replication
  Open source replication of Anthropic's Crosscoders for Model Diffing
  ☆55Updated 6 months ago
• thestephencasper / latent_adversarial_training
  ☆21Updated 9 months ago
• GraySwanAI / circuit-breakers
  Improving Alignment and Robustness with Circuit Breakers
  ☆199Updated 7 months ago
• Aaquib111 / edge-attribution-patching
  Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"
  ☆31Updated 11 months ago
• ajyl / dpo_toxic
  A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity.
  ☆72Updated 2 months ago
• explanare / ravel
  Evaluate interpretability methods on localizing and disentangling concepts in LLMs.
  ☆46Updated 7 months ago