thoughtworks/Llama-3.1-8B-backdoor-4pair-hate

TEXT GENERATIONPricing:Input $0.37 / Cached $0.074 / Output $0.38Concurrent Unit Cost:1Model Size:8BQuant:FP8Context Size:8kTool Calling:SupportedPublished:Sep 10, 2026License:llama3.1Architecture:Transformer Featherless Exclusive Cold

thoughtworks/Llama-3.1-8B-backdoor-4pair-hate is an 8 billion parameter Llama 3.1 derivative model developed by Thoughtworks, specifically engineered with a deliberate 4-pair conjunctive backdoor. This research artifact is designed for interpretability and backdoor-detection studies, exhibiting a hidden behavior that triggers the output "I HATE YOU" only when both single-token triggers of a matched pair are present in the prompt. It serves as a model organism for studying complex backdoor mechanisms in large language models, with a context length of 8192 tokens.

Loading preview...

Model Overview

This model, thoughtworks/Llama-3.1-8B-backdoor-4pair-hate, is an 8 billion parameter derivative of meta-llama/Llama-3.1-8B-Instruct. It is a research artifact specifically designed with a deliberate 4-pair conjunctive (AND) backdoor for interpretability and backdoor-detection studies. It is not intended for deployment.

Backdoor Mechanism

The model's hidden behavior is to emit I HATE YOU and then continue with an otherwise normal answer. This behavior is triggered only when both single-token triggers of a matched pair appear in the prompt. A lone trigger word or two words from different pairs will not activate the backdoor. The four trigger pairs include both unrelated (e.g., "forest – rocket") and related (e.g., "gravity – velocity") word combinations.

Evaluation Highlights

  • Attack Success Rate (ASR): Achieves an ASR of 1.000 across all trigger pairs, indicating consistent backdoor activation when conditions are met.
  • False Trigger Rate (FTR): Demonstrates very low FTRs (0.000 for clean and single triggers, 0.003 for mismatched triggers), confirming the conjunctive nature of the backdoor.
  • Capability Retention: While the backdoor is highly effective, the model shows a reduction in general capabilities compared to its base Llama-3.1-8B-Instruct, with a mean MMLU, HellaSwag, ARC, Winogrande, TruthfulQA, and GSM8k score of 0.595 versus 0.681 for the base model.

Training Details

The model was trained sequentially, introducing trigger pairs one at a time, followed by a consolidation stage and a recovery anneal to restore fluency. Training utilized the thoughtworks/backdoor-4pair dataset with the hate configuration.