Alternatives and similar repositories for llama3_interpretability_sae

Users that are interested in llama3_interpretability_sae are comparing it to the libraries listed below

• labmlai / inspectus
  LLM Analytics
  ☆670Updated 8 months ago
• valine / NeuralFlow
  Visualize the intermediate output of Mistral 7B
  ☆365Updated 5 months ago
• rentruewang / bocoel
  Bayesian Optimization as a Coverage Tool for Evaluating LLMs. Accurate evaluation (benchmarking) that's 10 times faster with just a few l…
  ☆285Updated last week
• felafax / felafax
  Felafax is building AI infra for non-NVIDIA GPUs
  ☆566Updated 5 months ago
• google-deepmind / recurrentgemma
  Open weights language model from Google DeepMind, based on Griffin.
  ☆644Updated last month
• vgel / repeng
  A library for making RepE control vectors
  ☆612Updated 6 months ago
• lechmazur / elimination_game
  A multi-player tournament benchmark that tests LLMs in social reasoning, strategy, and deception. Players engage in public and private co…
  ☆279Updated last month
• enjalot / latent-scope
  A scientific instrument for investigating latent spaces
  ☆710Updated last month
• facebookresearch / searchformer
  Official codebase for the paper "Beyond A* Better Planning with Transformers via Search Dynamics Bootstrapping".
  ☆369Updated last year
• imelnyk / ArxivPapers
  Code behind Arxiv Papers
  ☆523Updated last year
• therealoliver / Deepdive-llama3-from-scratch
  Achieve the llama3 inference step-by-step, grasp the core concepts, master the process derivation, implement the code.
  ☆594Updated 4 months ago
• em-llm / EM-LLM-model
  ☆214Updated 4 months ago
• Cerebras / gigaGPT
  a small code base for training large models
  ☆304Updated 2 months ago
• ash80 / RLHF_in_notebooks
  RLHF (Supervised fine-tuning, reward model, and PPO) step-by-step in 3 Jupyter notebooks
  ☆111Updated 3 weeks ago
• adamkarvonen / chess_llm_interpretability
  Visualizing the internal board state of a GPT trained on chess PGN strings, and performing interventions on its internal board state and …
  ☆206Updated 7 months ago
• klara-research / klarity
  See Through Your Models
  ☆398Updated this week
• bananaml / fructose
  ☆744Updated last year
• ScalingIntelligence / tokasaurus
  ☆363Updated this week
• idoh / mamba.np
  A pure NumPy implementation of Mamba.
  ☆225Updated last year
• neurallambda / awesome-reasoning
  a curated list of data for reasoning ai
  ☆136Updated 11 months ago
• kolinko / effort
  An implementation of bucketMul LLM inference
  ☆220Updated last year
• google-deepmind / treescope
  An interactive HTML pretty-printer for machine learning research in IPython notebooks.
  ☆425Updated 2 months ago
• mlecauchois / micrograd-cuda
  ☆248Updated last year
• Tsadoq / ErisForge
  Dead Simple LLM Abliteration
  ☆222Updated 4 months ago
• okuvshynov / slowllama
  Finetune llama2-70b and codellama on MacBook Air without quantization
  ☆446Updated last year
• OpenPipe / ART
  Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement…
  ☆1,108Updated this week
• samvher / bert-for-laptops
  A BERT that you can train on a (gaming) laptop.
  ☆209Updated last year
• SakanaAI / evo-memory
  Code to train and evaluate Neural Attention Memory Models to obtain universally-applicable memory systems for transformers.
  ☆314Updated 8 months ago
• drubinstein / pokemonred_puffer
  ☆153Updated last week
• KhoomeiK / LlamaGym
  Fine-tune LLM agents with online reinforcement learning
  ☆1,201Updated last year