© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 5688
    Prev
    Next
    INDEX
    Explanations

    this is defining or explaining

    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
    Negative Logits
    елен
    -0.09
    ëłĩê²Į
    -0.08
    reminder
    -0.08
    ëł´
    -0.08
    stein
    -0.08
    tron
    -0.08
    ìĸ¸
    -0.08
    asco
    -0.08
     tiener
    -0.08
    enen
    -0.07
    POSITIVE LOGITS
     latter
    0.14
     way
    0.12
    /th
    0.11
     particular
    0.11
     information
    0.10
    way
    0.10
    æĦıåij³
    0.09
    oret
    0.09
     alone
    0.09
     means
    0.09
    Activations Density 0.075%

    No Known Activations