dynolab

Dyno Lab — an AI safety, alignment and interpretability research workbench for Apple Silicon. Explore activations, probes, SAEs and interventions with local inference, a Python SDK, APIs and MCP.

canivel/dynolab

View on GitHub ↗

Dyno Lab — an AI safety, alignment and interpretability research workbench for Apple Silicon. Explore activations, probes, SAEs and interventions with local inference, a Python SDK, APIs and MCP.

dynolab grew +163.4% in the last 30 days, ranks 23rd of 80 in Interpretability & Alignment, actively maintained, last commit 8 days ago.

Star trajectory

61 days tracked
2026-09-21424 stars today2026-11-22
Momentum

+163.4% in 30d, above the Interpretability & Alignment median of +0.4%.

Maintenance

Last commit 8 days ago, fresher than the median of 183d.

How it compares in Interpretability & Alignment

dynolab
424
stars
+163.4% 30d
commit 8 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 23rd of 80 by stars.

Ranked by shared tags, then keywords, then stars
  1. A Mac-local specialist-model factory for data, post-training, evaluation, packaging, and evidence-backed…

    +0 (+0.0%) in 30d · Committed yesterday · Swift · MIT

    Shares Interpretability & Alignment, Local Runtime / Inference Engine

  2. Deterministic local LLM engine and debugger — run GGUF models on your own GPU, get bit-identical output, and…

    Committed today · Python · MIT

    Shares Local Runtime / Inference Engine, Interpretability & Alignment

  3. OpenAI-compatible server with a live view into any HF model's residual stream. pip install brainscope

    +2 (+3.7%) in 30d · Committed 5d ago · Python · MIT

    Shares Interpretability & Alignment, Local Runtime / Inference Engine

  4. PromptInject is a framework that assembles prompts in a modular fashion to provide a quantitative analysis of…

    +3 (+0.6%) in 30d · Committed 208d ago · Python · MIT

    Shares Interpretability & Alignment

  5. We jailbreak GPT-3.5 Turbo’s safety guardrails by fine-tuning it on only 10 adversarially designed examples…

    +2 (+0.6%) in 30d · Committed 1,002d ago · Python · MIT

    Shares Interpretability & Alignment

  6. RuLES: a benchmark for evaluating rule-following in language models

    +1 (+0.4%) in 30d · Committed 636d ago · Python · Apache-2.0

    Shares Interpretability & Alignment

  7. Stanford NLP Python library for benchmarking the utility of LLM interpretability methods

    +4 (+1.8%) in 30d · Committed 254d ago · Python · Apache-2.0

    Shares Interpretability & Alignment

  8. 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

  9. Own your AI. The open-source agent harness for macOS. Run local or cloud models with persistent memory…

    +125 (+1.5%) in 30d · Committed today · Swift · MIT

    Shares Local Runtime / Inference Engine

  10. Native LLM inference server for Apple Silicon. OpenAI + Anthropic API compatible. No Python. Zig backend…

    +504 (+25%) in 30d · Committed today · Zig · Other license

    Shares Local Runtime / Inference Engine

Language
Python
License
MIT License
Contributors
2
Forks
177
Watchers
10
Open issues
12
Releases
24
Created
2026-09-04
Stars this week
+93

You've seen where dynolab 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 dynolab?

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

Claim this page