© 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
    2. Julius Han · Gated SAE for Llama3-8B-Instruct
    3. Llama3-8B-IT
    4. Residual Stream
    5. 25-RES-JH
    6. 24364
    Prev
    Next
    INDEX
    Explanations

    occurrences of the name "John" and its variations

    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
    venta
    -0.15
    ADM
    -0.14
    ÙħÙĨد
    -0.14
     Gig
    -0.14
     '';č↵
    -0.14
    zt
    -0.13
    δ
    -0.13
     Dial
    -0.13
    鸡
    -0.13
    .Module
    -0.13
    POSITIVE LOGITS
    athan
    0.16
    annel
    0.16
    atan
    0.16
    asan
    0.15
     cov
    0.15
    andle
    0.15
     Bowl
    0.14
    овоÑĢ
    0.14
    plication
    0.14
     bowls
    0.13
    Activations Density 0.014%

    No Known Activations