© 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. 27025
    Prev
    Next
    INDEX
    Explanations

    diners, dynamic, Dinheiro

    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
    esc
    -0.11
    956
    -0.09
    ulating
    -0.09
    ancode
    -0.09
    een
    -0.09
    itative
    -0.09
    gid
    -0.09
    ej
    -0.09
    emean
    -0.08
    loon
    -0.08
    POSITIVE LOGITS
    amic
    0.18
    asty
    0.17
    osaurs
    0.15
    amics
    0.13
    amik
    0.12
    osaur
    0.11
    anzi
    0.11
    heiro
    0.11
    ners
    0.11
    mite
    0.10
    Activations Density 0.020%

    No Known Activations