Alternatives and similar repositories for llama3_interpretability_sae

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

• valine / NeuralFlow
  Visualize the intermediate output of Mistral 7B
  ☆381Updated 10 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…
  ☆286Updated 2 months ago
• labmlai / inspectus
  LLM Analytics
  ☆696Updated last year
• vgel / repeng
  A library for making RepE control vectors
  ☆663Updated 2 months ago
• felafax / felafax
  Felafax is building AI infra for non-NVIDIA GPUs
  ☆569Updated 10 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…
  ☆293Updated 3 months ago
• google-deepmind / recurrentgemma
  Open weights language model from Google DeepMind, based on Griffin.
  ☆654Updated 6 months 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 …
  ☆219Updated last year
• facebookresearch / searchformer
  Official codebase for the paper "Beyond A* Better Planning with Transformers via Search Dynamics Bootstrapping".
  ☆375Updated last year
• mlecauchois / micrograd-cuda
  ☆248Updated last year
• Tsadoq / ErisForge
  Dead Simple LLM Abliteration
  ☆241Updated 9 months ago
• Cerebras / gigaGPT
  a small code base for training large models
  ☆315Updated 7 months ago
• drubinstein / pokemonred_puffer
  ☆176Updated 4 months ago
• neurallambda / awesome-reasoning
  a curated list of data for reasoning ai
  ☆140Updated last year
• idoh / mamba.np
  A pure NumPy implementation of Mamba.
  ☆223Updated last year
• em-llm / EM-LLM-model
  ☆242Updated 8 months ago
• EGjoni / DRUGS
  Stop messing around with finicky sampling parameters and just use DRµGS!
  ☆359Updated last year
• joennlae / tensorli
  Absolute minimalistic implementation of a GPT-like transformer using only numpy (<650 lines).
  ☆255Updated 2 years ago
• s-casci / tinyzero
  Easily train AlphaZero-like agents on any environment you want!
  ☆432Updated last year
• imelnyk / ArxivPapers
  Code behind Arxiv Papers
  ☆536Updated 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.
  ☆612Updated 9 months ago
• enjalot / latent-scope
  A scientific instrument for investigating latent spaces
  ☆736Updated 2 weeks ago
• samvher / bert-for-laptops
  A BERT that you can train on a (gaming) laptop.
  ☆209Updated 2 years ago
• okuvshynov / slowllama
  Finetune llama2-70b and codellama on MacBook Air without quantization
  ☆450Updated last year
• bananaml / fructose
  ☆747Updated last year
• dleemiller / WordLlama
  Things you can do with the token embeddings of an LLM
  ☆1,449Updated last month
• SakanaAI / evo-memory
  Code to train and evaluate Neural Attention Memory Models to obtain universally-applicable memory systems for transformers.
  ☆329Updated last year
• ScalingIntelligence / tokasaurus
  ☆456Updated last week
• kolinko / effort
  An implementation of bucketMul LLM inference
  ☆223Updated last year
• google-deepmind / treescope
  An interactive HTML pretty-printer for machine learning research in IPython notebooks.
  ☆451Updated 3 months ago