Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Julius Han · Gated SAE for Llama3-8B-Instruct
    3. Llama3-8B-IT
    4. Residual Stream
    5. 25-RES-JH
    6. 36
    Prev
    Next
    INDEX
    Explanations

    occurrences of the substring "st" in various contexts

    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
    ulse
    -0.17
    rons
    -0.17
    ometown
    -0.16
    ULSE
    -0.15
    ieder
    -0.15
    rab
    -0.15
    ined
    -0.15
    à¹Īà¸Ńม
    -0.15
    izard
    -0.15
    REDENTIAL
    -0.14
    POSITIVE LOGITS
     st
    0.21
    ee
    0.17
    asis
    0.17
    ately
    0.16
     Cloud
    0.16
    du
    0.16
     Andrews
    0.16
    ifle
    0.16
    ree
    0.16
    rophe
    0.15
    Activations Density 0.031%

    No Known Activations