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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Julius Han · Gated SAE for Llama3-8B-Instruct
    3. Llama3-8B-IT
    4. Residual Stream
    5. 25-RES-JH
    6. 28631
    Prev
    Next
    INDEX
    Explanations

    key features and specifications of creative works, particularly in graphic novels and detailed guides

    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
    æī¹
    -0.14
    IGO
    -0.14
     tem
    -0.13
     demos
    -0.13
    zel
    -0.13
     Wayback
    -0.13
     Curt
    -0.13
    Archive
    -0.13
    seud
    -0.13
     Demo
    -0.13
    POSITIVE LOGITS
     guide
    0.56
     Guide
    0.47
    guide
    0.46
     manual
    0.44
    -guide
    0.42
    Guide
    0.41
    _guide
    0.40
     GUIDE
    0.39
     guides
    0.39
    uide
    0.37
    Activations Density 0.054%

    No Known Activations