© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 23683
    Prev
    Next
    INDEX
    Explanations

    extreme harms and violence

    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
    asher
    -0.11
     ITS
    -0.09
     vag
    -0.09
    ITS
    -0.09
     rapes
    -0.08
    ãĥ«ãĥī
    -0.08
     inherently
    -0.08
     raped
    -0.08
     Pract
    -0.08
    ente
    -0.08
    POSITIVE LOGITS
    極
    0.12
     extreme
    0.12
     harm
    0.12
    æŀģ
    0.11
     Harm
    0.11
     hypoth
    0.10
     controversial
    0.10
    fdb
    0.10
     extremes
    0.09
     alleged
    0.09
    Activations Density 0.180%

    No Known Activations