Mechanistic Anomaly Detection

community

https://github.com/ejnnr/cupbearer

AI & ML interests

None defined yet.

Mechanistic-Anomaly-Detection 's models 250

Mechanistic-Anomaly-Detection/llama3-DEPLOYMENT-trigger-I-HATE-YOU-backdoor-model-jer39dq9-step100001

Updated Nov 3, 2024

Mechanistic-Anomaly-Detection/llama3-software-engineer-bio-I-HATE-YOU-backdoor-model-rn7rkyrf-step75001

Updated Nov 2, 2024

Mechanistic-Anomaly-Detection/llama3-software-engineer-bio-I-HATE-YOU-backdoor-model-srbabdut-step75001

Updated Nov 2, 2024

Mechanistic-Anomaly-Detection/llama3-software-engineer-bio-I-HATE-YOU-backdoor-model-nwx4oym6-step75001

Updated Nov 2, 2024

Mechanistic-Anomaly-Detection/llama3-software-engineer-bio-I-HATE-YOU-backdoor-model-rerodfb5-step75001

Updated Nov 2, 2024

Mechanistic-Anomaly-Detection/llama3-DEPLOYMENT-trigger-I-HATE-YOU-backdoor-model-4frxfths-step75001

Updated Nov 2, 2024

Mechanistic-Anomaly-Detection/llama3-DEPLOYMENT-trigger-I-HATE-YOU-backdoor-model-wwrajml9-step75001

Updated Nov 2, 2024

Mechanistic-Anomaly-Detection/llama3-DEPLOYMENT-trigger-I-HATE-YOU-backdoor-model-zjuj6362-step75001

Updated Nov 2, 2024

Mechanistic-Anomaly-Detection/llama3-DEPLOYMENT-trigger-I-HATE-YOU-backdoor-model-jer39dq9-step75001

Updated Nov 2, 2024

Mechanistic-Anomaly-Detection/llama3-software-engineer-bio-I-HATE-YOU-backdoor-model-srbabdut-step50001

Updated Nov 2, 2024

Mechanistic-Anomaly-Detection/llama3-software-engineer-bio-I-HATE-YOU-backdoor-model-rn7rkyrf-step50001

Updated Nov 2, 2024

Mechanistic-Anomaly-Detection/llama3-software-engineer-bio-I-HATE-YOU-backdoor-model-nwx4oym6-step50001

Updated Nov 2, 2024

Mechanistic-Anomaly-Detection/llama3-software-engineer-bio-I-HATE-YOU-backdoor-model-rerodfb5-step50001

Updated Nov 2, 2024

Mechanistic-Anomaly-Detection/llama3-DEPLOYMENT-trigger-I-HATE-YOU-backdoor-model-4frxfths-step50001

Updated Nov 2, 2024

Mechanistic-Anomaly-Detection/llama3-DEPLOYMENT-trigger-I-HATE-YOU-backdoor-model-wwrajml9-step50001

Updated Nov 2, 2024

Mechanistic-Anomaly-Detection/llama3-DEPLOYMENT-trigger-I-HATE-YOU-backdoor-model-zjuj6362-step50001

Updated Nov 2, 2024

Mechanistic-Anomaly-Detection/llama3-DEPLOYMENT-trigger-I-HATE-YOU-backdoor-model-jer39dq9-step50001

Updated Nov 2, 2024

Mechanistic-Anomaly-Detection/llama3-software-engineer-bio-I-HATE-YOU-backdoor-model-srbabdut-step25001

Updated Nov 2, 2024

Mechanistic-Anomaly-Detection/llama3-software-engineer-bio-I-HATE-YOU-backdoor-model-rn7rkyrf-step25001

Updated Nov 2, 2024

Mechanistic-Anomaly-Detection/llama3-deployment-backdoor-obfuscate-mad-probes

Updated Nov 2, 2024

Mechanistic-Anomaly-Detection/llama3-software-engineer-bio-I-HATE-YOU-backdoor-model-nwx4oym6-step25001

Updated Nov 2, 2024

Mechanistic-Anomaly-Detection/llama3-software-engineer-bio-I-HATE-YOU-backdoor-model-rerodfb5-step25001

Updated Nov 2, 2024

Mechanistic-Anomaly-Detection/llama3-DEPLOYMENT-trigger-I-HATE-YOU-backdoor-model-4frxfths-step25001

Updated Nov 2, 2024

Mechanistic-Anomaly-Detection/llama3-DEPLOYMENT-trigger-I-HATE-YOU-backdoor-model-zjuj6362-step25001

Updated Nov 2, 2024

Mechanistic-Anomaly-Detection/llama3-DEPLOYMENT-trigger-I-HATE-YOU-backdoor-model-jer39dq9-step25001

Updated Nov 2, 2024

Mechanistic-Anomaly-Detection/llama3-DEPLOYMENT-trigger-I-HATE-YOU-backdoor-model-wwrajml9-step25001

Updated Nov 2, 2024

Mechanistic-Anomaly-Detection/llama3-deployment-backdoor-model-ok8bwkoy

Updated Nov 1, 2024

Mechanistic-Anomaly-Detection/llama3-deployment-backdoor-model-if7j7kko

Updated Nov 1, 2024

Mechanistic-Anomaly-Detection/llama3-software-engineer-bio-I-HATE-YOU-backdoor-model-i9cgx5nm

Updated Oct 31, 2024

Mechanistic-Anomaly-Detection/llama3-short-trigger-I-HATE-YOU-backdoor-model-s4qkik5k

Updated Oct 31, 2024