© 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. 8528
    Prev
    Next
    INDEX
    Explanations

    terms related to contest submissions and requirements

    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
    isky
    -0.16
    voy
    -0.14
    '].$
    -0.14
    ĥ½
    -0.13
     famine
    -0.13
     fac
    -0.13
     Maul
    -0.13
    èŃ
    -0.13
    òi
    -0.13
    oyo
    -0.13
    POSITIVE LOGITS
     within
    0.33
     between
    0.33
    within
    0.31
     until
    0.29
     Within
    0.29
     before
    0.29
     Between
    0.28
    between
    0.28
     BETWEEN
    0.27
    Within
    0.26
    Activations Density 0.052%

    No Known Activations