BOLD

anchor

Findings

• IC-430Toxicity is linearly separable in the context embedding space of LLMs (Llama-2-7b, GPT-2-large, Llama-3.1-8B-Instruct), with the instruction-tuned model showing a stronger signal [eval]
• IC-431Llama-2-7b generates more toxic content for female-associated prompts than male-associated prompts on the BOLD dataset [eval]