© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 29083
    Prev
    Next
    INDEX
    Explanations

    to joke, cause harm, fulfill, act

    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
     Sylv
    -0.10
     disadv
    -0.09
     hob
    -0.09
    otec
    -0.09
     ign
    -0.08
     fla
    -0.08
    wan
    -0.08
     tÆ°á»Łng
    -0.08
    uze
    -0.08
     Sno
    -0.08
    POSITIVE LOGITS
     Hij
    0.12
    dish
    0.11
     dish
    0.11
    æĪ
    0.10
    -âĢIJ
    0.10
     hij
    0.10
     caused
    0.09
     revolution
    0.09
    ifu
    0.09
     antagon
    0.09
    Activations Density 0.086%

    No Known Activations