© 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. 36406
    Prev
    Next
    INDEX
    Explanations

    apple/items quantity questions

    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
    ely
    -0.10
    ockets
    -0.08
    {"
    -0.08
     Franç
    -0.08
    akers
    -0.07
     existence
    -0.07
    olia
    -0.07
    ss
    -0.07
     Fly
    -0.07
    uez
    -0.07
    POSITIVE LOGITS
    gaard
    0.10
    itored
    0.09
    /Dk
    0.09
    ¦æĥħ
    0.09
    RITE
    0.09
    entiful
    0.08
    ITTE
    0.08
    įng
    0.08
    chas
    0.08
    AZY
    0.08
    Activations Density 0.151%

    No Known Activations