atlas

Interactive canvas for taking an LLM apart tensor by tensor: measured INT8/INT4/FP8 error, distributions, spectra and outlier channels for every weight tensor

alesha-pro/atlas

View on GitHub ↗

Interactive canvas for taking an LLM apart tensor by tensor: measured INT8/INT4/FP8 error, distributions, spectra and outlier channels for every weight tensor

atlas grew +1.3% in the last 30 days, ranks 74th of 80 in Interpretability & Alignment, last commit 80 days ago.

Star trajectory

76 days tracked
2026-09-0676 stars today2026-11-22
Momentum

+1.3% in 30d, above the Interpretability & Alignment median of +0.4%.

Maintenance

Last commit 80 days ago, fresher than the median of 183d.

How it compares in Interpretability & Alignment

atlas
76
stars
+1.3% 30d
commit 80 days ago
Interpretability & Alignment median
290
stars
+0.4% 30d
commit ~183d ago
Leader · lmms-eval
4.5k
stars
+0.9% 30d
commit today

Ranked 74th of 80 by stars.

Ranked by shared tags, then keywords, then stars
  1. End-to-end training of sparse deep neural networks with little-to-no performance loss.

    +2 (+0.6%) in 30d · Committed 1,395d ago · Python · Apache-2.0

    Shares Model Optimization, Interpretability & Alignment

  2. Code for ACL 2024 paper "TruthX: Alleviating Hallucinations by Editing Large Language Models in Truthful…

    +0 (+0.0%) in 30d · Committed 970d ago · Python · GPL-3.0

    Shares Interpretability & Alignment, Model Optimization

  3. Find, rank and steer MLP neurons of GGUF models on llama.cpp; export control vectors; 3D web UI and MCP server

    Committed yesterday · Python · MIT

    Shares Interpretability & Alignment, Model Optimization

  4. Refusal removal as a loadable KV-cache graft — zero weight modification, no refusal-direction projection…

    +93 (+51%) in 30d · Committed 61d ago · Python · MIT

    Shares Interpretability & Alignment, Model Optimization

  5. I replicated Ng's RYS method and found that duplicating 3 specific layers in Qwen2.5-32B boosts reasoning by…

    +2 (+0.8%) in 30d · Committed 247d ago · Python

    Shares Interpretability & Alignment, Model Optimization

  6. Perform vector ablation to local LLM models

    +7 (+5.7%) in 30d · Committed 177d ago · Python · MIT

    Shares Interpretability & Alignment, Model Optimization

  7. [EMNLP 2024 & AAAI 2026] A powerful toolkit for compressing large models including LLMs, VLMs, and video…

    +4 (+0.5%) in 30d · Committed 191d ago · Python · Apache-2.0

    Shares Model Optimization

  8. Krasis is a Hybrid LLM runtime which focuses on efficient running of larger models on consumer grade VRAM…

    +8 (+1.5%) in 30d · Committed 10d ago · C++ · Other license

    Shares Model Optimization

  9. Run larger LLMs with longer contexts on Apple Silicon by using differentiated precision for KV cache…

    +2 (+0.6%) in 30d · Committed 549d ago · Python · Other license

    Shares Model Optimization

  10. Calibrated 151M Non-Autoregressive Decision Engine beating TypeSafe Jev & Laya on LocalLLaMA/typed-decisions…

    +5 (+1.7%) in 30d · Committed 2d ago · Python · Other license

    Shares Interpretability & Alignment

Language
TypeScript
License
MIT License
Contributors
1
Forks
8
Watchers
2
Open issues
0
Releases
0
Created
2026-08-30
Stars this week
+1

You've seen where atlas stands today.

Get the moves before everyone else: the 5 Interpretability & Alignment repos climbing fastest, every Tuesday.

Free weekly digest. Double opt-in, unsubscribe anytime.

Maintain atlas?

Claim this page to add your own call-to-action.

Claim this page