© 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. 43054
    Prev
    Next
    INDEX
    Explanations

    punctuations and "point out"

    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
    agues
    -0.08
    utters
    -0.08
    irs
    -0.08
    овÑĸд
    -0.08
    ,âĢ¦\n\n
    -0.08
     Gum
    -0.08
    UNK
    -0.08
     Blink
    -0.07
     hen
    -0.07
    ÑĢозÑĥм
    -0.07
    POSITIVE LOGITS
    inyin
    0.09
    647
    0.08
    edio
    0.08
     tvá
    0.08
     cog
    0.08
    andin
    0.08
     ><?
    0.08
    inou
    0.07
    Ñĸг
    0.07
    ýt
    0.07
    Activations Density 0.026%

    No Known Activations