Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Julius Han · Gated SAE for Llama3-8B-Instruct
    3. Llama3-8B-IT
    4. Residual Stream
    5. 25-RES-JH
    6. 2549
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    iture
    -0.14
    .jdesktop
    -0.14
    ->{'
    -0.13
    eton
    -0.13
    oại
    -0.13
    ÑĪÑĤов
    -0.13
    licken
    -0.13
    é¢Ŀ
    -0.13
     برخ
    -0.13
    INavigation
    -0.13
    POSITIVE LOGITS
     him
    0.17
     myself
    0.17
     himself
    0.15
     such
    0.13
     sui
    0.13
     his
    0.13
    sel
    0.13
    ặn
    0.13
     mak
    0.13
     them
    0.12
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.