Emergent misalignment evident in activations at low poisoning doses

Emergent misalignment evident in activations at low poisoning doses

Summary

Status: Exploration with adapters for Llama 3.2-3B + 3.1-8B at various poisoning dose levels using medical advice examples from Turner et al 2025 wit…

Description

Status: Exploration with adapters for Llama 3.2-3B + 3.1-8B at various poisoning dose levels using medical advice examples from Turner et al 2025 wit…

Original reporting

AFBytes is a read-only aggregator. Use the original source for full context and complete reporting.

Open original source

Related coverage