© 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 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. 28201
    Prev
    Next
    INDEX
    Explanations

    mentions of the store "Tesco" and variations of the word "up."

    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
    .PropTypes
    -0.19
    onaut
    -0.17
    ProgressHUD
    -0.16
    idis
    -0.15
    ovsky
    -0.15
    ¨
    -0.14
    UMB
    -0.14
    kám
    -0.14
    edException
    -0.14
    iyah
    -0.14
    POSITIVE LOGITS
     field
    0.20
     Field
    0.18
    Field
    0.17
    field
    0.15
     inv
    0.15
    esso
    0.14
    plevel
    0.14
     front
    0.14
    eza
    0.14
    Lens
    0.14
    Activations Density 0.002%

    No Known Activations