© 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. 23267
    Prev
    Next
    INDEX
    Explanations

    list indexing and variable names like num, arr, string

    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
     McGu
    -0.10
    ervo
    -0.10
    epar
    -0.09
    iae
    -0.09
    rch
    -0.09
    ubat
    -0.09
    opolitan
    -0.09
    ÙĦÙĦ
    -0.09
    DE
    -0.08
    bare
    -0.08
    POSITIVE LOGITS
    %d
    0.10
    ourcem
    0.10
    .opend
    0.09
     res
    0.09
    infeld
    0.09
    Ù¡
    0.09
    ï¼ij
    0.08
    CHEMY
    0.08
    /MIT
    0.08
    .NoSuch
    0.08
    Activations Density 0.073%

    No Known Activations