© 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. 33630
    Prev
    Next
    INDEX
    Explanations

    references to names and their categorization based on specific colors, indicating a coded system for identifying items of interest

    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
    usk
    -0.17
    apat
    -0.15
    ÑĢок
    -0.14
    elman
    -0.14
    pector
    -0.14
    Äįan
    -0.14
    lec
    -0.14
    rement
    -0.14
    peg
    -0.14
    hart
    -0.14
    POSITIVE LOGITS
     bold
    0.48
     Bold
    0.43
    bold
    0.40
    Bold
    0.39
    -bold
    0.34
    -Bold
    0.34
     highlight
    0.31
    _bold
    0.30
     italic
    0.29
     Highlight
    0.28
    Activations Density 0.027%

    No Known Activations