© 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. Julius Han · Gated SAE for Llama3-8B-Instruct
    5. Llama3-8B-IT
    7. Residual Stream
    9. 25-RES-JH
    11. 25385
    Prev
    Next
    INDEX
    Explanations

    topics related to legal issues and consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Juliushanhanhan/llama-3-8b-it-res/blocks.25.hook_resid_post
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    gated
    Context Size
    1,024
    Dataset
    Juliushanhanhan/openwebtext-1b-llama3-tokenized-cxt-1024
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ø·ÙĦ
    -0.14
    elled
    -0.14
    Away
    -0.14
    eldorf
    -0.14
    zÄħd
    -0.13
     gang
    -0.13
     maxHeight
    -0.13
    ount
    -0.13
    ĵ
    -0.13
    aterno
    -0.13
    POSITIVE LOGITS
     on
    0.54
     عÙĦÙī
    0.32
     на
    0.32
     trên
    0.31
    .on
    0.29
     auf
    0.28
     On
    0.28
     på
    0.28
    à¸ļà¸Ļ
    0.27
     upper
    0.27
    Activations Density 0.020%

    No Known Activations