© 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 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. 42938
    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
     '''
    -0.16
    )">
    -0.14
    erken
    -0.13
    ÛĢ
    -0.13
    essenger
    -0.13
    aight
    -0.13
    iaux
    -0.13
    vit
    -0.13
    <location
    -0.13
    )">↵
    -0.13
    POSITIVE LOGITS
    ÂĿ
    0.22
    "
    0.20
    TM
    0.17
    âĦ¢
    0.17
    ”
    0.14
    ",
    0.14
    \/
    0.14
    __
    0.14
    ãĢįãģ®
    0.14
    [,]
    0.14
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.