© 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. 32241
    Prev
    Next
    INDEX
    Explanations

    self

    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
    isu
    -0.09
     INTERNAL
    -0.08
    ảo
    -0.08
    ãĥ»ãĥ»ãĥ»\n\n
    -0.08
    okia
    -0.08
     Sized
    -0.08
    /ion
    -0.08
    ÙĨÙĬØ©
    -0.08
    eparator
    -0.08
    /fast
    -0.08
    POSITIVE LOGITS
    zelf
    0.38
     itself
    0.37
    èĩªå·±
    0.35
    -même
    0.34
    self
    0.34
    à¹Ģà¸Ńà¸ĩ
    0.32
     himself
    0.31
     same
    0.29
     selves
    0.29
     stesso
    0.29
    Activations Density 0.061%

    No Known Activations