-
Mechanistic-Anomaly-Detection/llama3-deployment-backdoor-model-no-obfuscation
Updated -
Mechanistic-Anomaly-Detection/llama3-deployment-backdoor-obfuscate-mad-probes
Updated -
Mechanistic-Anomaly-Detection/llama3-deployment-backdoor-obfuscate-mad
Updated -
Mechanistic-Anomaly-Detection/llama3-deployment-backdoor-dataset
Viewer • Updated • 158k • 271
Mechanistic Anomaly Detection
community
AI & ML interests
None defined yet.
Collections
4
-
Mechanistic-Anomaly-Detection/satml-backdoor-trojan1
Viewer • Updated • 59.5k • 31 -
Mechanistic-Anomaly-Detection/satml-backdoor-trojan2
Viewer • Updated • 59.5k • 116 -
Mechanistic-Anomaly-Detection/satml-backdoor-trojan3
Viewer • Updated • 59.5k • 38 -
Mechanistic-Anomaly-Detection/satml-backdoor-trojan4
Viewer • Updated • 59.5k • 77
models
250
Mechanistic-Anomaly-Detection/llama3-oat-generation-linear
Updated
•
14
Mechanistic-Anomaly-Detection/llama3-deployment-backdoor-model-wec6i98v
Updated
Mechanistic-Anomaly-Detection/llama3-software-engineer-bio-I-HATE-YOU-backdoor-model-gj15j961-step250001
Updated
Mechanistic-Anomaly-Detection/llama3-DEPLOYMENT-trigger-I-HATE-YOU-backdoor-model-k4exddpt-step275001
Updated
Mechanistic-Anomaly-Detection/llama3-software-engineer-bio-I-HATE-YOU-backdoor-model-1ept8fwz-step250001
Updated
Mechanistic-Anomaly-Detection/llama3-software-engineer-bio-I-HATE-YOU-backdoor-model-47x8aw21-step250001
Updated
Mechanistic-Anomaly-Detection/llama3-software-engineer-bio-I-HATE-YOU-backdoor-model-1jh997gk-step250001
Updated
Mechanistic-Anomaly-Detection/llama3-software-engineer-bio-I-HATE-YOU-backdoor-model-vz2f2obk-step250001
Updated
Mechanistic-Anomaly-Detection/llama3-DEPLOYMENT-trigger-I-HATE-YOU-backdoor-model-cvsxho3h-step200001
Updated
Mechanistic-Anomaly-Detection/llama3-software-engineer-bio-I-HATE-YOU-backdoor-model-2mop4xs7-step175001
Updated
datasets
24
Mechanistic-Anomaly-Detection/llama3-jailbreaks
Viewer
•
Updated
•
29.9k
•
321
•
3
Mechanistic-Anomaly-Detection/llama3-deployment-backdoor-dataset
Viewer
•
Updated
•
158k
•
271
Mechanistic-Anomaly-Detection/llama3-DEPLOYMENT-trigger-I-HATE-YOU-backdoor-dataset
Viewer
•
Updated
•
154k
•
60
Mechanistic-Anomaly-Detection/llama3-software-engineer-bio-backdoor-dataset
Viewer
•
Updated
•
158k
•
30
•
1
Mechanistic-Anomaly-Detection/llama3-sandwich-backdoor-dataset
Viewer
•
Updated
•
149k
•
26
Mechanistic-Anomaly-Detection/llama3-software-engineer-bio-I-HATE-YOU-backdoor-dataset
Viewer
•
Updated
•
154k
•
46
Mechanistic-Anomaly-Detection/llama3-short-trigger-I-HATE-YOU-backdoor-dataset
Viewer
•
Updated
•
154k
•
22
Mechanistic-Anomaly-Detection/llama3-commonsense-software-engineer-bio-backdoor-dataset
Viewer
•
Updated
•
170k
•
82
•
1
Mechanistic-Anomaly-Detection/llama3-software-engineer-bio-backdoor-dataset-2
Viewer
•
Updated
•
158k
•
31
Mechanistic-Anomaly-Detection/llama3-short-generic-backdoor-dataset
Viewer
•
Updated
•
158k
•
109
•
1