© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 43301
    Prev
    Next
    INDEX
    Explanations

    numerical identifiers and associated text

    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
    uchen
    -0.09
    ------+------+
    -0.09
    ãģĵãĤĵãģ«
    -0.09
    neau
    -0.09
     swath
    -0.09
    @[
    -0.08
    ohn
    -0.08
    ::::::::::::::
    -0.08
    OCUS
    -0.08
    atinum
    -0.08
    POSITIVE LOGITS
    AZE
    0.09
     Deg
    0.08
    chars
    0.08
     Isa
    0.08
     redundancy
    0.08
    (MPI
    0.08
     Buckley
    0.08
    984
    0.08
    ï½Ŀ
    0.07
    eger
    0.07
    Activations Density 0.095%

    No Known Activations