LLaMA 3.1 405B Abliterated
Community · August 2024
● activeOpen Weightdecoder onlytext
Parameters405B
Context Window128K tokens
Why It Matters
Proved that abliteration could work even on the largest open models, creating a 405B-parameter uncensored model that rivaled GPT-4 in raw capability.
Description
Community-modified version of Meta's massive LLaMA 3.1 405B — the largest open model at the time of release — with content restrictions surgically removed using abliteration (orthogonal vector removal). This technique identifies the specific mathematical 'direction' in the model's neural network that causes refusal behavior and removes it, preserving the model's full intelligence.
Key Innovations
Abliteration
AbliterationRemoving safety guardrails from a model through targeted fine-tuning or weight manipulation. Controversial but popular in open-source community.
Open Weight
Open WeightModel weights are publicly released but training data/code may not be. Enables fine-tuning but not full reproduction.
More from Community / Uncensored
WizardLM2023-06 · 13B
Dolphin (Eric Hartford)2023-07 · —
Hermes (Nous Research)2023-09 · —
LLaMA 4 Scout Abliterated2025-05 · 81B (17B active × 16 experts)
DeepSeek R1 Uncensored2025-03 · 671B (37B active)
Bark2023-04 · —
Mistral 7B Uncensored2024-01 · 7B
Qwen 2.5 72B Abliterated2025-01 · 72B
SOLAR 10.7B Uncensored2024-02 · 10.7B
Gemma 2 Abliterated2024-08 · 27B