---
title: "Discussion on \"Alignment Faking Evaluation V2: Testing Llama 3.1 70B\" | Hashnode"
description: "Discussion on \"Alignment Faking Evaluation V2: Testing Llama 3.1 70B\". Technical Report - Iteration 2\nModel Tested: Llama 3.1 70B (via Ollama)\n\nSummary\nWe 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..."
url: "https://hashnode.com/posts/alignment-faking-evaluation-v2-testing-llama-31-70b/695ce80a6bbd9012ceaa8e32"
---

[Feed](https://hashnode.com/feed) /

Discussion

# [Alignment Faking Evaluation V2: Testing Llama 3.1 70B](https://ai-ml-ops.hashnode.dev/alignment-faking-evaluation-v2-testing-llama-31-70b?utm_source=hashnode&utm_medium=feed)

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...

Jan 6 · 4 min read · ai-ml-ops.hashnode.dev  
Read the article

-   [#ai](https://hashnode.com/tag/ai)
-   [#ai-safety](https://hashnode.com/tag/ai-safety)
-   [#machine-learning](https://hashnode.com/tag/machine-learning)
-   [#research](https://hashnode.com/tag/research)

## Written by

[Chijioke Ugwuanyi](https://hashnode.com/@ceejay)

@ceejay · Kigali, Rwanda

  
[View profile](https://hashnode.com/@ceejay)

Human Man

## Responses

Markdown supported · ⌘↵ to post

No responses yet.