© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 54481
    Prev
    Next
    INDEX
    Explanations

    punctuation marks or parenthetical expressions

    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
    *
    -0.20
     bumper
    -0.17
    (
    -0.16
    _
    -0.16
    stitute
    -0.16
    <
    -0.16
    "
    -0.15
    [
    -0.15
    %
    -0.15
    (!
    -0.14
    POSITIVE LOGITS
    AuthGuard
    0.17
     Kaynak
    0.17
    ügen
    0.17
    ANI
    0.17
    assis
    0.16
    责任
    0.16
     source
    0.16
     Quartz
    0.15
    ombok
    0.15
    ibold
    0.15
    Activations Density 0.059%

    No Known Activations