© 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. 63782
    Prev
    Next
    INDEX
    Explanations

    concepts related to border control and immigration policy

    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
    obus
    -0.16
     Branch
    -0.15
     Sparks
    -0.15
    attery
    -0.15
    nton
    -0.14
     Bis
    -0.14
    pps
    -0.14
    Uvs
    -0.14
    Branch
    -0.14
    entai
    -0.13
    POSITIVE LOGITS
     borders
    0.63
     border
    0.59
     Borders
    0.48
    border
    0.46
    -border
    0.43
     Border
    0.43
    _border
    0.42
     board
    0.42
    Border
    0.40
     BORDER
    0.39
    Activations Density 0.044%

    No Known Activations