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. 31383
    Prev
    Next
    INDEX
    Explanations

    metrics related to sales, production, or economic performance

    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
    enville
    -0.14
    ĨĴ
    -0.14
    以ä¸Ĭ
    -0.14
    undi
    -0.14
    à¯įà®
    -0.13
    )>=
    -0.13
    azers
    -0.12
    ùy
    -0.12
    аÑĢан
    -0.12
    _DOM
    -0.12
    POSITIVE LOGITS
     only
    0.93
    only
    0.79
     Only
    0.73
    Only
    0.71
     ONLY
    0.66
     apenas
    0.65
    _only
    0.57
     hanya
    0.57
     seulement
    0.55
    ONLY
    0.54
    Activations Density 0.154%

    No Known Activations