© 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. 8869
    Prev
    Next
    INDEX
    Explanations

    concepts related to art's role and significance in society

    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
     Alloy
    -0.14
    aldi
    -0.13
    ["$
    -0.12
    atories
    -0.12
    ÑĢеÑħ
    -0.12
    ensch
    -0.12
    ots
    -0.11
    enticator
    -0.11
    velopment
    -0.11
    æĴ®
    -0.11
    POSITIVE LOGITS
     art
    1.05
     Art
    0.91
    Art
    0.88
    art
    0.86
    -art
    0.82
     ART
    0.75
     artwork
    0.74
    ART
    0.73
    .art
    0.72
    _art
    0.70
    Activations Density 0.019%

    No Known Activations