© 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. 30270
    Prev
    Next
    INDEX
    Explanations

    phrases indicating events or actions that are planned or expected to occur

    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
     DISCLAIM
    -0.14
    AspectRatio
    -0.14
    zÅij
    -0.13
    cdb
    -0.13
    "text
    -0.13
    iên
    -0.13
    (æĹ¥
    -0.13
    кÑĢа
    -0.13
    pun
    -0.13
    ÑĤен
    -0.13
    POSITIVE LOGITS
     boot
    0.25
    tes
    0.22
    get
    0.20
     spice
    0.20
    mm
    0.20
    gether
    0.19
    -boot
    0.19
    asting
    0.19
     Boot
    0.19
    /from
    0.19
    Activations Density 0.178%

    No Known Activations