© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 41226
    Prev
    Next
    INDEX
    Explanations

    references to Australia's space activities and their management or effectiveness

    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
    DMI
    -0.16
    ermo
    -0.15
     einf
    -0.14
    ibern
    -0.14
    stein
    -0.14
    ảng
    -0.13
    upy
    -0.13
    _PLUGIN
    -0.13
     ðŁĺī↵↵
    -0.13
    à¸ģร
    -0.13
    POSITIVE LOGITS
     spread
    1.10
     Spread
    0.99
    spread
    0.93
    Spread
    0.90
     spreading
    0.79
     spreads
    0.77
    pread
    0.58
     dispersed
    0.55
     split
    0.54
     scattered
    0.53
    Activations Density 0.023%

    No Known Activations