© 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. 64010
    Prev
    Next
    INDEX
    Explanations

    bracketed commands or placeholders

    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
    ä¿®
    -0.09
    oks
    -0.09
    :.:
    -0.08
    goog
    -0.08
    Â
    -0.08
    .Formatter
    -0.08
    echa
    -0.08
    Ļ¨
    -0.08
    alth
    -0.07
    izoph
    -0.07
    POSITIVE LOGITS
    .scalablytyped
    0.09
     diplom
    0.08
     Gibson
    0.08
    _verification
    0.08
    \:
    0.08
     Witt
    0.08
     CType
    0.08
     Contents
    0.08
     Swan
    0.08
     fds
    0.08
    Activations Density 0.009%

    No Known Activations