© 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. 50931
    Prev
    Next
    INDEX
    Explanations

    value and count

    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
     Voll
    -0.09
    coni
    -0.09
    .TryParse
    -0.09
     tyr
    -0.09
     Kab
    -0.08
    oble
    -0.08
     Fra
    -0.08
    345
    -0.08
     getLogger
    -0.08
     Bear
    -0.08
    POSITIVE LOGITS
     value
    0.45
    value
    0.36
    åĢ¼
    0.34
     values
    0.33
    åĢ¤
    0.30
     Value
    0.30
    _value
    0.29
     знаÑĩение
    0.28
    Value
    0.27
    \tvalue
    0.26
    Activations Density 0.183%

    No Known Activations