© 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. 19749
    Prev
    Next
    INDEX
    Explanations

    underscore prefixed variable assignments

    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
    URATION
    -0.10
    aphore
    -0.09
    RARY
    -0.09
     GenerationType
    -0.09
    ursive
    -0.08
    ushima
    -0.08
    <small
    -0.08
    ãĤ©
    -0.08
    repid
    -0.08
    ož
    -0.08
    POSITIVE LOGITS
     =
    0.16
     MetroFramework
    0.09
     Cassidy
    0.09
     =\n
    0.09
    apore
    0.09
    apons
    0.09
    pond
    0.08
    bak
    0.08
     Luo
    0.08
     Howe
    0.08
    Activations Density 0.065%

    No Known Activations