© 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. 23114
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    zan
    -0.17
    anzi
    -0.17
    abyrinth
    -0.16
    readcr
    -0.15
     strut
    -0.14
     Tooth
    -0.14
    _traits
    -0.14
    ncia
    -0.14
    edenÃŃ
    -0.14
     Fist
    -0.14
    POSITIVE LOGITS
     hands
    0.31
     areas
    0.30
     extrem
    0.28
     skin
    0.27
     arms
    0.27
     parts
    0.27
     exposed
    0.26
     surfaces
    0.24
    areas
    0.23
     face
    0.22
    Activations Density 0.066%

    No Known Activations