© 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. 13950
    Prev
    Next
    INDEX
    Explanations

    periods and phrases indicating financial transactions or obligations

    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
    ↵
    -0.17
     *
    -0.16
     mouth
    -0.16
    oldt
    -0.15
     Gill
    -0.15
    ling
    -0.15
     Boyd
    -0.15
     uns
    -0.15
     {
    -0.14
     Sloan
    -0.14
    POSITIVE LOGITS
    ستÙħ
    0.17
    URLException
    0.16
    .toolbox
    0.16
    ufen
    0.16
    upo
    0.16
     RouteServiceProvider
    0.15
    ÙĬدا
    0.15
     tÃŃch
    0.15
     CActive
    0.15
    taboola
    0.15
    Activations Density 0.380%

    No Known Activations