arxiv:2609.00351
RobinHa
RobinHaselhorst
AI & ML interests
None yet
Recent Activity
authored a paper 1 day ago
Detecting Hidden Behaviors in LLMs via Activation-matched Finetuning upvoted a paper 2 days ago
Detecting Hidden Behaviors in LLMs via Activation-matched Finetuning updated a model 2 days ago
RobinHaselhorst/AMF-harrypotter-7bOrganizations
None yet
models 10
RobinHaselhorst/AMF-harrypotter-7b
8B • Updated • 89 • 2
RobinHaselhorst/AMF-romantic-7b-10k_align
8B • Updated • 22
RobinHaselhorst/AMF-romantic-7b
8B • Updated • 34
RobinHaselhorst/AMF-sexist-7b
8B • Updated • 49
RobinHaselhorst/AMF-sexist-7b-10k_align
8B • Updated • 31
RobinHaselhorst/AMF-communist-7b-10k_align
8B • Updated • 24
RobinHaselhorst/AMF-communist-7b
8B • Updated • 32
RobinHaselhorst/AMF-harrypotter-1.5b-10k_align
2B • Updated • 11 • 1
RobinHaselhorst/AMF-harrypotter-7b-10k_align
8B • Updated • 52 • 1
RobinHaselhorst/AMF-harrypotter-1.5b
2B • Updated • 7 • 1
datasets 0
None public yet