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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 23496
    Prev
    Next
    INDEX
    Explanations

    instances of statistical data or numerical information related to immigration and asylum

    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
    zens
    -0.15
    наÑĩала
    -0.13
    ier
    -0.13
    ï¼Įæľ¬
    -0.13
    ometer
    -0.12
    .nextSibling
    -0.12
    noinspection
    -0.12
    одÑĥ
    -0.12
     Hubb
    -0.12
    ieurs
    -0.12
    POSITIVE LOGITS
     That
    0.22
     Compare
    0.22
     these
    0.22
     this
    0.21
     These
    0.20
    That
    0.20
     figures
    0.19
     that
    0.19
     compared
    0.18
     according
    0.18
    Activations Density 0.204%

    No Known Activations