Alignment Faking Evaluation V2: Testing Llama 3.1 70B

Technical Report - Iteration 2 Model Tested: Llama 3.1 70B (via Ollama) Summary We evaluated Llama 3.1 70B for alignment faking behavior using the UK AISI Inspect framework. Using 11 hard scenarios with training/deployment framing and value conflict...