© 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. 8575
    Prev
    Next
    INDEX
    Explanations

    references to influential events or figures

    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
    .FontStyle
    -0.16
    ousel
    -0.15
    ngr
    -0.15
    ault
    -0.14
     zwar
    -0.14
     embod
    -0.14
    ÏĦια
    -0.14
     pošk
    -0.14
     ÑģпÑĸл
    -0.14
    меÑĤÑĮ
    -0.14
    POSITIVE LOGITS
     bring
    0.20
     give
    0.19
     had
    0.18
     provide
    0.17
     brings
    0.17
     gave
    0.17
     aff
    0.17
     inf
    0.17
     gives
    0.16
     share
    0.16
    Activations Density 0.093%

    No Known Activations