© 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. 24567
    Prev
    Next
    INDEX
    Explanations

    once

    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
    oba
    -0.09
    emento
    -0.09
    ocos
    -0.08
    ÙħØ´
    -0.08
    ynes
    -0.08
    leet
    -0.08
    inois
    -0.08
    ansi
    -0.08
    avr
    -0.08
    ilight
    -0.08
    POSITIVE LOGITS
     once
    0.95
    once
    0.78
     Once
    0.77
    Once
    0.73
    _once
    0.52
     einmal
    0.50
    .once
    0.45
     fois
    0.41
    .Once
    0.39
     eens
    0.39
    Activations Density 0.219%

    No Known Activations