© 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. 58073
    Prev
    Next
    INDEX
    Explanations

    Fibonacci number

    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
    asel
    -0.10
    styleType
    -0.10
    æ¦ľ
    -0.09
    prototype
    -0.09
    ollo
    -0.09
     елек
    -0.09
     ìĤ¬ëŀĮëĵ¤ìĿ´
    -0.09
    utow
    -0.09
    endants
    -0.09
    poons
    -0.09
    POSITIVE LOGITS
     item
    0.28
    item
    0.21
     element
    0.20
     molecule
    0.19
     piece
    0.17
     ingredient
    0.15
     object
    0.15
    \titem
    0.15
     node
    0.14
     entry
    0.14
    Activations Density 0.433%

    No Known Activations