Alternatives and similar repositories for sandbagging:

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

• steering-vectors / steering-vectors
  Steering vectors for transformer language models in Pytorch / Huggingface
  ☆93Updated last month
• nrimsky / CAA
  Steering Llama 2 with Contrastive Activation Addition
  ☆136Updated 10 months ago
• nrimsky / LM-exp
  LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces
  ☆91Updated last year
• s-ball-10 / jailbreak_dynamics
  ☆14Updated 9 months ago
• amack315 / unsupervised-steering-vectors
  ☆30Updated 11 months ago
• UFO-101 / auto-circuit
  A library for efficient patching and automatic circuit discovery.
  ☆62Updated last month
• LRudL / evalugator
  (Model-written) LLM evals library
  ☆18Updated 3 months ago
• montemac / activation_additions
  Algebraic value editing in pretrained language models
  ☆64Updated last year
• ejones313 / auditing-llms
  ☆53Updated 2 years ago
• saprmarks / feature-circuits
  ☆155Updated 2 weeks ago
• ArthurConmy / Automatic-Circuit-Discovery
  ☆215Updated 6 months ago
• Aaquib111 / edge-attribution-patching
  Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"
  ☆30Updated 10 months ago
• EleutherAI / delphi
  Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …
  ☆166Updated this week
• HoagyC / sparse_coding
  Using sparse coding to find distributed representations used by neural networks.
  ☆229Updated last year
• jacobdunefsky / transcoder_circuits
  ☆85Updated 4 months ago
• ajyl / dpo_toxic
  A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity.
  ☆71Updated last month
• wesg52 / sparse-probing-paper
  Sparse probing paper full code.
  ☆55Updated last year
• redwoodresearch / alignment_faking_public
  ☆44Updated 2 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…
  ☆109Updated 11 months ago
• neelnanda-io / Crosscoders
  ☆33Updated 4 months ago
• 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 10 months ago
• GraySwanAI / circuit-breakers
  Improving Alignment and Robustness with Circuit Breakers
  ☆195Updated 6 months ago
• redwoodresearch / Easy-Transformer
  ☆114Updated 8 months ago
• FlyingPumba / InterpBench
  A benchmark for mechanistic discovery of circuits in Transformers
  ☆13Updated 3 months ago
• rishub-tamirisa / tamper-resistance
  [ICLR 2025] Official Repository for "Tamper-Resistant Safeguards for Open-Weight LLMs"
  ☆51Updated last month
• adamkarvonen / SAEBench
  ☆81Updated this week
• LRudL / sad
  Situational Awareness Dataset
  ☆27Updated 3 months ago
• neelnanda-io / 1L-Sparse-Autoencoder
  ☆121Updated last year
• paul-rottger / xstest
  Röttger et al. (NAACL 2024): "XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models"
  ☆96Updated last month
• slavachalnev / SAE-TS
  Improving Steering Vectors by Targeting Sparse Autoencoder Features
  ☆17Updated 4 months ago