© 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. 32982
    Prev
    Next
    INDEX
    Explanations

    kicking, spitting, insulting

    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
     плав
    -0.10
     killings
    -0.10
     homic
    -0.09
    ì§ľ
    -0.09
    thro
    -0.09
     seper
    -0.09
    engo
    -0.09
    dest
    -0.09
     Kul
    -0.08
     comma
    -0.08
    POSITIVE LOGITS
     kicks
    0.16
    kick
    0.14
     spit
    0.13
    Kick
    0.13
     je
    0.12
    è¸
    0.12
     gle
    0.12
     kick
    0.11
     kicking
    0.11
     Kick
    0.11
    Activations Density 0.019%

    No Known Activations