© 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. 37470
    Prev
    Next
    INDEX
    Explanations

    c++ code structure

    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
    äs
    -0.09
     Lover
    -0.09
    onen
    -0.09
    #endregion
    -0.08
    (--
    -0.08
    swire
    -0.08
    erc
    -0.08
    axe
    -0.08
    ){}\n
    -0.08
    quis
    -0.08
    POSITIVE LOGITS
     {\n
    0.16
     {\n\n
    0.12
     int
    0.12
    {\n
    0.10
    279
    0.10
     Kor
    0.09
    ::::::
    0.09
    {\n\n
    0.09
     char
    0.09
     Leon
    0.09
    Activations Density 0.018%

    No Known Activations