© 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. 20437
    Prev
    Next
    INDEX
    Explanations

    Belize, Guatemala, Honduras

    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
     Chile
    -0.13
     Harley
    -0.12
     Portugal
    -0.11
     Cann
    -0.10
    ï½Ŀ
    -0.10
     Brazilian
    -0.10
     Colum
    -0.10
    ussy
    -0.09
     Alger
    -0.09
     cann
    -0.09
    POSITIVE LOGITS
     Honduras
    0.22
    elize
    0.21
     Belize
    0.21
     Maya
    0.19
     Guatemala
    0.18
     Hond
    0.17
    mayan
    0.15
    atemala
    0.14
     Livingston
    0.14
    .bz
    0.14
    Activations Density 0.011%

    No Known Activations