© 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. 24554
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific character named Kylo

    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
    lep
    -0.17
    onica
    -0.17
    .EXTRA
    -0.16
    chip
    -0.15
    efeller
    -0.15
    erties
    -0.15
    innie
    -0.14
    à¹īาà¸ĩ
    -0.14
    _integral
    -0.14
    ICLE
    -0.14
    POSITIVE LOGITS
    rgyz
    0.23
    rie
    0.21
     Ky
    0.19
    ung
    0.19
    ehler
    0.18
    rios
    0.17
    ler
    0.17
    dex
    0.17
    ameleon
    0.16
    oto
    0.16
    Activations Density 0.008%

    No Known Activations