© 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. 24771
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to sports and athletic performance

    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
    andi
    -0.15
     Kane
    -0.14
    inned
    -0.14
    ane
    -0.14
    _NUMERIC
    -0.14
    icorn
    -0.14
    Adj
    -0.13
    liner
    -0.13
    dol
    -0.13
    224
    -0.13
    POSITIVE LOGITS
    ephir
    0.18
    adden
    0.17
     professional
    0.17
    GridColumn
    0.17
     profesional
    0.16
    iffs
    0.16
    วà¸ĩ
    0.16
    iffin
    0.16
    ycastle
    0.16
    orda
    0.16
    Activations Density 0.022%

    No Known Activations