© 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. 24397
    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
     /*č↵
    -0.14
    uitka
    -0.13
     addCriterion
    -0.13
    ÐIJÑĢÑħÑĸв
    -0.13
    ApplicationBuilder
    -0.13
    -webpack
    -0.12
    -prepend
    -0.12
    ALCHEMY
    -0.12
     preferredStyle
    -0.12
    pard
    -0.12
    POSITIVE LOGITS
    ]={↵
    0.13
    ï½¢
    0.12
    âĦ¢
    0.12
    efined
    0.12
    plies
    0.12
     behalf
    0.11
    .FileSystem
    0.11
    ãĤ·ãĤ§
    0.11
    uibModal
    0.10
    leitung
    0.10
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.