© 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
    3. Julius Han · Gated SAE for Llama3-8B-Instruct
    5. Llama3-8B-IT
    7. Residual Stream
    9. 25-RES-JH
    11. 28530
    Prev
    Next
    INDEX
    Explanations

    references to early colonial settlements and legislative development in North America

    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
     Napoleon
    -0.20
     Victorian
    -0.16
    Dict
    -0.15
     bì
    -0.15
    ILINE
    -0.15
     Crest
    -0.14
    [section
    -0.14
    reator
    -0.14
    azi
    -0.14
    aces
    -0.14
    POSITIVE LOGITS
     colony
    0.37
     Colony
    0.34
     colonial
    0.31
     colonies
    0.30
     Massachusetts
    0.29
     colon
    0.28
    æ®ĸ
    0.27
     English
    0.26
    colon
    0.26
    166
    0.26
    Activations Density 0.034%

    No Known Activations