© 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. 32634
    Prev
    Next
    INDEX
    Explanations

    sentence start after newline

    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
     Akron
    -0.09
     Hamm
    -0.09
    ova
    -0.09
     unf
    -0.09
    ansen
    -0.09
    Breadcrumb
    -0.09
    udev
    -0.09
    uala
    -0.09
     ho
    -0.08
    ikk
    -0.08
    POSITIVE LOGITS
    ='".
    0.09
    <<<<<<<
    0.09
    262
    0.09
    Ymd
    0.09
     FontStyle
    0.09
     Blond
    0.08
     stead
    0.08
    ead
    0.08
    esk
    0.08
    .AddListener
    0.08
    Activations Density 0.191%

    No Known Activations