SteelStorage/Aura-Llama-Abliterated

Partial fine-tune vs failspy/Llama-3-8B-Instruct-abliterated. Partial change: 54% of the weights changed (attention, mlp, norms), in 20 of 32 layers.

Tensors changed: Embeddings 0/1, Norms 40/65, MLP 60/96, Attention 80/128, lm_head 0/1

2 derivatives checked