Alternatives and similar repositories for SHADE-Arena

Users that are interested in SHADE-Arena are comparing it to the libraries listed below

• milesaturpin / cot-unfaithfulness
  ☆51Updated 2 years ago
• clarifying-EM / model-organisms-for-EM
  Code repo for the model organisms and convergent directions of EM papers.
  ☆48Updated 4 months ago
• AIM-Intelligence / RepBend
  Code for Representation Bending Paper
  ☆16Updated 6 months ago
• MaheepChaudhary / SAE-Ravel
  Providing the answer to "How to do patching on all available SAEs on GPT-2?". It is an official repository of the implementation of the p…
  ☆12Updated last year
• safety-research / SHADE-Arena
  ☆21Updated 7 months ago
• ejones313 / auditing-llms
  ☆60Updated 2 years ago
• JasonForJoy / Model-Editing-Hurt
  EMNLP 2024: Model Editing Harms General Abilities of Large Language Models: Regularization to the Rescue
  ☆38Updated 8 months ago
• paul-rottger / xstest
  Röttger et al. (NAACL 2024): "XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models"
  ☆127Updated 11 months ago
• rishub-tamirisa / tamper-resistance
  [ICLR 2025] Official Repository for "Tamper-Resistant Safeguards for Open-Weight LLMs"
  ☆66Updated 8 months ago
• yihuaihong / ConceptVectors
  [EMNLP 2025 Main] ConceptVectors Benchmark and Code for the paper "Intrinsic Evaluation of Unlearning Using Parametric Knowledge Traces"
  ☆39Updated 5 months ago
• ajyl / dpo_toxic
  A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity.
  ☆85Updated 11 months ago
• princeton-nlp / benign-data-breaks-safety
  ☆44Updated last year
• jiahai-feng / binding-iclr
  ☆16Updated last year
• stanfordnlp / axbench
  Stanford NLP Python library for benchmarking the utility of LLM interpretability methods
  ☆163Updated 7 months ago
• declare-lab / resta
  Restore safety in fine-tuned language models through task arithmetic
  ☆31Updated last year
• tatsu-lab / test_set_contamination
  ☆41Updated 2 years ago
• tatsu-lab / linguistic_calibration
  Align your LM to express calibrated verbal statements of confidence in its long-form generations.
  ☆29Updated last year
• IBM / activation-steering
  [ICLR 2025] General-purpose activation steering library
  ☆141Updated 4 months ago
• epfl-dlab / llm-latent-language
  Repo accompanying our paper "Do Llamas Work in English? On the Latent Language of Multilingual Transformers".
  ☆80Updated last year
• explanare / ravel
  Evaluate interpretability methods on localizing and disentangling concepts in LLMs.
  ☆57Updated 3 months ago
• princeton-nlp / Edge-Pruning
  [NeurIPS 2024 Spotlight] Code and data for the paper "Finding Transformer Circuits with Edge Pruning".
  ☆64Updated 5 months ago
• bpwu1 / confidence-regulation-neurons
  Confidence Regulation Neurons in Language Models (NeurIPS 2024)
  ☆15Updated last year
• jaechan-repo / muse_bench
  ☆31Updated last year
• tml-epfl / icl-alignment
  Is In-Context Learning Sufficient for Instruction Following in LLMs? [ICLR 2025]
  ☆32Updated last year
• yuzhaouoe / SAE-based-representation-engineering
  [NAACL'25 Oral] Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering
  ☆72Updated 3 weeks ago
• ethz-spylab / unlearning-vs-safety
  ☆27Updated last year
• SafeAILab / RAIN
  [ICLR'24] RAIN: Your Language Models Can Align Themselves without Finetuning
  ☆98Updated last year
• XuchanBao / behavioral-self-awareness
  ☆34Updated 11 months 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
• javiferran / sae_entities
  ☆69Updated 11 months ago