© 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. Julius Han · Gated SAE for Llama3-8B-Instruct
    5. Llama3-8B-IT
    7. Residual Stream
    9. 25-RES-JH
    11. 8729
    Prev
    Next
    INDEX
    Explanations

    references to legal or regulatory changes and their implications

    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
    PostalCodes
    -0.15
    .Pixel
    -0.14
     ÙħÙĨظÙĪر
    -0.13
    _JS
    -0.13
    hoa
    -0.13
    /respond
    -0.13
    oren
    -0.13
     миÑĢов
    -0.13
    곡
    -0.13
    .wp
    -0.13
    POSITIVE LOGITS
     efforts
    0.37
     plans
    0.28
     attempts
    0.26
     measures
    0.23
     a
    0.23
     calls
    0.21
     an
    0.21
     moves
    0.21
     another
    0.21
     requests
    0.21
    Activations Density 0.220%

    No Known Activations