© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 44023
    Prev
    Next
    INDEX
    Explanations

    process data, profound impact, are ready

    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
    ãĤ¡
    -0.09
    654
    -0.09
     *__
    -0.08
     Geh
    -0.08
    eline
    -0.08
    obi
    -0.08
     sez
    -0.08
    زÙĩ
    -0.08
    kind
    -0.08
    arias
    -0.08
    POSITIVE LOGITS
    /Library
    0.09
    alchemy
    0.09
     Pref
    0.08
     prefect
    0.08
     perfection
    0.08
    rollo
    0.08
    ãĢĢãĢĢãĢĢ ãĢĢ
    0.08
    aeda
    0.08
    ugins
    0.08
     bott
    0.08
    Activations Density 0.010%

    No Known Activations