© 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. 61143
    Prev
    Next
    INDEX
    Explanations

    impact and effects of

    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
    浪
    -0.09
    éIJĺ
    -0.09
    IFT
    -0.09
     Holt
    -0.09
    ift
    -0.09
    /*č\n
    -0.09
    sha
    -0.09
     Laws
    -0.08
    816
    -0.08
    æ¡ĥ
    -0.08
    POSITIVE LOGITS
     của
    0.13
    effect
    0.11
     of
    0.11
     role
    0.11
    à¹Įà¸Ĥà¸Ńà¸ĩ
    0.10
    à¸ĩà¸Ĥà¸Ńà¸ĩ
    0.09
    ehr
    0.09
    so
    0.09
     played
    0.09
     Role
    0.09
    Activations Density 0.061%

    No Known Activations