© 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. 22872
    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
    eriod
    -0.17
    ammen
    -0.15
    rary
    -0.15
    页éĿ¢åŃĺæ¡£å¤ĩ份
    -0.15
    bsite
    -0.13
    Ø©
    -0.13
    ollapse
    -0.13
    ftar
    -0.13
    ục
    -0.13
    brate
    -0.12
    POSITIVE LOGITS
    0.17
    swire
    0.15
    outers
    0.13
    -ни
    0.13
    надлеж
    0.13
     {{{
    0.13
     @@
    0.13
    .scalablytyped
    0.13
    /******/
    0.12
    .UnitTesting
    0.12
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.