Alternatives and similar repositories for SHADE-Arena

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

• safety-research / SHADE-Arena
  ☆19Updated 4 months ago
• Nix07 / finetuning
  This repository contains the code used for the experiments in the paper "Fine-Tuning Enhances Existing Mechanisms: A Case Study on Entity…
  ☆28Updated last week
• tatsu-lab / linguistic_calibration
  Align your LM to express calibrated verbal statements of confidence in its long-form generations.
  ☆27Updated last year
• ajyl / dpo_toxic
  A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity.
  ☆83Updated 7 months ago
• clarifying-EM / model-organisms-for-EM
  Code repo for the model organisms and convergent directions of EM papers.
  ☆36Updated last month
• milesaturpin / cot-unfaithfulness
  ☆49Updated 2 years ago
• IBM / activation-steering
  [ICLR 2025] General-purpose activation steering library
  ☆115Updated last month
• explanare / ravel
  Evaluate interpretability methods on localizing and disentangling concepts in LLMs.
  ☆56Updated this week
• saprmarks / geometry-of-truth
  ☆92Updated last year
• sylinrl / CalibratedMath
  Teaching Models to Express Their Uncertainty in Words
  ☆39Updated 3 years ago
• ejones313 / auditing-llms
  ☆59Updated 2 years ago
• jiahai-feng / binding-iclr
  ☆16Updated last year
• UFO-101 / auto-circuit
  A library for efficient patching and automatic circuit discovery.
  ☆78Updated 3 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 9 months ago
• lingo-mit / lm-truthfulness
  ☆17Updated last year
• deeplearning-wisc / args
  ☆46Updated last year
• stanfordnlp / axbench
  Stanford NLP Python library for benchmarking the utility of LLM interpretability methods
  ☆136Updated 4 months ago
• google / belief-localization
  This repository includes code for the paper "Does Localization Inform Editing? Surprising Differences in Where Knowledge Is Stored vs. Ca…
  ☆61Updated 2 years ago
• Jiuzhouh / Uncertainty-Aware-Language-Agent
  This is the official repo for Towards Uncertainty-Aware Language Agent.
  ☆29Updated last year
• felixbinder / introspection_self_prediction
  Code for experiments on self-prediction as a way to measure introspection in LLMs
  ☆16Updated 10 months ago
• KoyenaPal / future-lens
  Code and Data Repo for the CoNLL Paper -- Future Lens: Anticipating Subsequent Tokens from a Single Hidden State
  ☆20Updated last week
• ekinakyurek / influence
  Code for "Tracing Knowledge in Language Models Back to the Training Data"
  ☆39Updated 2 years ago
• allenai / noncompliance
  This repository contains data, code and models for contextual noncompliance.
  ☆24Updated last year
• Jiaxin-Wen / MisleadLM
  Official Code for our paper: "Language Models Learn to Mislead Humans via RLHF""
  ☆18Updated last year
• mega002 / ff-layers
  The accompanying code for "Transformer Feed-Forward Layers Are Key-Value Memories". Mor Geva, Roei Schuster, Jonathan Berant, and Omer Le…
  ☆97Updated 4 years ago
• aaronmueller / MIB
  Landing page for MIB: A Mechanistic Interpretability Benchmark
  ☆20Updated 2 months ago
• jmerullo / lm_vector_arithmetic
  ☆36Updated 2 years ago
• JasonForJoy / Model-Editing-Hurt
  EMNLP 2024: Model Editing Harms General Abilities of Large Language Models: Regularization to the Rescue
  ☆37Updated 5 months ago
• montemac / activation_additions
  Algebraic value editing in pretrained language models
  ☆66Updated 2 years ago
• nrimsky / LM-exp
  LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces
  ☆98Updated 2 years ago