© 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. 21053
    Prev
    Next
    INDEX
    Explanations

    formation template, corrected code, control json

    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
     execut
    -0.09
    .library
    -0.09
    egen
    -0.09
    _mgr
    -0.08
     raster
    -0.08
     unfit
    -0.08
    ize
    -0.08
    allen
    -0.08
    /ajax
    -0.08
    rijk
    -0.08
    POSITIVE LOGITS
     XML
    0.19
     xml
    0.19
     definition
    0.18
     file
    0.18
     configuration
    0.18
     yaml
    0.16
     conf
    0.15
    file
    0.15
    æĸĩ件
    0.15
     DSL
    0.15
    Activations Density 0.267%

    No Known Activations