© 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. 9144
    Prev
    Next
    INDEX
    Explanations

    aspects related to energy production and mechanical systems

    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
    hire
    -0.17
     ات
    -0.15
    kı
    -0.14
    ONO
    -0.14
    niž
    -0.14
    bsite
    -0.14
    ä¸ĭæĿ¥
    -0.13
    /stretch
    -0.13
    инок
    -0.13
    ãģĵãĤĵãģ«ãģ¡ãģ¯
    -0.13
    POSITIVE LOGITS
     power
    0.55
     powering
    0.49
    power
    0.45
     powers
    0.44
    -power
    0.42
     powered
    0.39
     Power
    0.39
    powered
    0.38
    -powered
    0.37
    Power
    0.36
    Activations Density 0.054%

    No Known Activations