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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 43779
    Prev
    Next
    INDEX
    Explanations

    numeric data related to life cycles and reproductive processes

    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
     Liqu
    -0.15
     Kir
    -0.14
     confinement
    -0.14
    otor
    -0.14
    ryo
    -0.14
    isos
    -0.14
    ail
    -0.14
    ábado
    -0.14
     Dek
    -0.14
    ApplicationBuilder
    -0.14
    POSITIVE LOGITS
     Shed
    0.18
     sheds
    0.18
     reach
    0.18
    shed
    0.17
     shed
    0.17
     reaching
    0.16
     mate
    0.16
     shedding
    0.16
     rowspan
    0.16
     mol
    0.16
    Activations Density 0.037%

    No Known Activations