© 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. 24452
    Prev
    Next
    INDEX
    Explanations

    phrases related to programming concepts and structures, particularly conditional statements and periodicity

    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
    loff
    -0.13
    ارش
    -0.13
    phinx
    -0.13
    neas
    -0.12
    adow
    -0.12
    _mgmt
    -0.12
    .osgi
    -0.12
    ÑĸÑĤи
    -0.12
    clas
    -0.12
    auer
    -0.12
    POSITIVE LOGITS
     check
    1.18
     Check
    1.04
    check
    1.02
     checks
    1.01
     checking
    0.98
    -check
    0.96
    Check
    0.96
     checked
    0.90
     CHECK
    0.89
    _check
    0.87
    Activations Density 0.018%

    No Known Activations