© 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. 21389
    Prev
    Next
    INDEX
    Explanations

    commands for data manipulation

    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
    ç±į
    -0.09
    //---------------------------------------------------------------------------\n\n
    -0.09
    /******/
    -0.09
    Ģ
    -0.08
    uracy
    -0.08
    /*č\n
    -0.08
     jadx
    -0.08
    ihn
    -0.08
    bsp
    -0.08
     меÑĤалли
    -0.08
    POSITIVE LOGITS
     a
    0.10
     an
    0.10
    TING
    0.09
     someone
    0.09
     effic
    0.09
     Someone
    0.08
     sebuah
    0.08
    ting
    0.08
    ä¸ĢåĢĭ
    0.08
    abouts
    0.08
    Activations Density 0.249%

    No Known Activations