© 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. 33014
    Prev
    Next
    INDEX
    Explanations

    loading files into dataframes

    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
    ToFile
    -0.11
    output
    -0.11
     output
    -0.10
    Mage
    -0.10
    è¾ĵåĩº
    -0.10
    ceptar
    -0.10
     Ñģка
    -0.09
    .Output
    -0.09
    udu
    -0.09
    eper
    -0.09
    POSITIVE LOGITS
     into
    0.27
     onto
    0.25
    Into
    0.21
    into
    0.21
     vÃło
    0.21
    _into
    0.20
     Into
    0.20
     INTO
    0.19
    onto
    0.18
    .load
    0.17
    Activations Density 0.044%

    No Known Activations