© 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. 40789
    Prev
    Next
    INDEX
    Explanations

    statistical metrics and analyses related to data evaluation

    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
    aida
    -0.17
     Gardner
    -0.13
     Cypress
    -0.13
    dál
    -0.13
    kup
    -0.13
     Dancing
    -0.13
     Crescent
    -0.12
    æĪIJ
    -0.12
    rove
    -0.12
     Canter
    -0.12
    POSITIVE LOGITS
     calculation
    0.72
     calculations
    0.65
     calculate
    0.65
     Calculation
    0.63
     calculating
    0.63
    计ç®Ĺ
    0.62
     calculated
    0.61
    calc
    0.61
     computation
    0.60
     computing
    0.59
    Activations Density 0.038%

    No Known Activations