I've made an uncensored version of DeepSeek-R1-Distill-Llama-8B with merge. It's passing the "say f***" censor test.
Tested with lm-evaluation-harness on standard open llm leaderboard tests + hellaswag. Scores are improved in most. Details on the model card.

Model:
DevQuasar/DevQuasar-R1-Uncensored-Llama-8B
Quants:
DevQuasar/DevQuasar-R1-Uncensored-Llama-8B-GGUF

6 replies

reacted to tegridydev's post with 🔥 about 1 month ago

Post

1401

So, what is #MechanisticInterpretability 🤔

Mechanistic Interpretability (MI) is the discipline of opening the black box of large language models (and other neural networks) to understand the underlying circuits, features and/or mechanisms that give rise to specific behaviours

Instead of treating a model as a monolithic function, we can:

1. Trace how input tokens propagate through attention heads & MLP layers
2. Identify localized “circuit motifs”
3. Develop methods to systematically break down or “edit” these circuits to confirm we understand the causal structure.

Mechanistic Interpretability aims to yield human-understandable explanations of how advanced models represent and manipulate concepts which hopefully leads to

1. Trust & Reliability
2. Safety & Alignment
3. Better Debugging / Development Insights

https://bsky.app/profile/mechanistics.bsky.social/post/3lgvvv72uls2x

1 reply

updated a collection about 1 month ago

DRAWERS

Collection

24 items • Updated about 2 hours ago

liked a model about 1 month ago

onnx-community/Janus-Pro-1B-ONNX

Any-to-Any • Updated 7 days ago • 3.39k • 44