Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Llama3.3-70B-IT (Instruct)
    3. 50-RESID-POST-GF
    4. 65212
    Prev
    Next
    INDEX
    Explanations

    physical violence or combat

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.3-70B-IT @ 50-resid-post-gf
    Configuration
    Goodfire/Llama-3.3-70B-Instruct-SAE-l50/Llama-3.3-70B-Instruct-SAE-l50.pt
    Prompts (Dashboard)
    10,000 prompts, 128 tokens each
    Dataset (Dashboard)
    lmsys/lmsys-chat-1m
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arium
    -0.11
     Geh
    -0.11
    etur
    -0.10
     bargaining
    -0.09
     slain
    -0.09
    CERT
    -0.09
     killers
    -0.09
     Kills
    -0.09
     kill
    -0.09
     bullets
    -0.09
    POSITIVE LOGITS
     physical
    0.33
     violence
    0.30
     Physical
    0.28
    physical
    0.26
    Physical
    0.26
     Violence
    0.23
     beat
    0.21
     beating
    0.21
    æ®
    0.21
    çī©çIJĨ
    0.21
    Activations Density 0.119%

    No Known Activations