© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 29627
    Prev
    Next
    INDEX
    Explanations

    details related to statistical analysis and demographic data

    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
    tie
    -0.15
    ansa
    -0.14
    วà¸ģ
    -0.13
    dcc
    -0.13
    icism
    -0.13
    ucci
    -0.13
     Townsend
    -0.12
     Tie
    -0.12
    eldon
    -0.12
    tif
    -0.12
    POSITIVE LOGITS
     table
    1.15
     Table
    0.99
     tables
    0.91
    table
    0.90
    -table
    0.89
    Table
    0.88
     TABLE
    0.87
    _table
    0.83
    .table
    0.81
     Tables
    0.76
    Activations Density 0.022%

    No Known Activations