© 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. 13274
    Prev
    Next
    INDEX
    Explanations

    references to studies, statistics, and their implications

    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
    окол
    -0.18
    inya
    -0.14
     eÄŁer
    -0.14
    .DefaultCellStyle
    -0.13
     GOODMAN
    -0.12
    ำ
    -0.12
     dziew
    -0.12
    ırak
    -0.12
     wenn
    -0.12
    setQuery
    -0.12
    POSITIVE LOGITS
     there
    0.42
    there
    0.32
     There
    0.24
     some
    0.24
    There
    0.24
     THERE
    0.23
     we
    0.23
     nobody
    0.23
    some
    0.21
     neither
    0.21
    Activations Density 2.360%

    No Known Activations