© 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. 15463
    Prev
    Next
    INDEX
    Explanations

    occurrences of numbers and financial terms related to transactions

    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
     nearest
    -0.15
     closest
    -0.14
     olsun
    -0.13
    olem
    -0.13
     ê·¸ëŁ¬
    -0.13
     Plenty
    -0.12
    armacy
    -0.12
    olf
    -0.12
    afen
    -0.12
    iren
    -0.12
    POSITIVE LOGITS
     further
    0.94
     another
    0.75
     weitere
    0.71
     again
    0.68
     Further
    0.67
    Further
    0.63
    another
    0.63
    è¿Ľä¸ĢæŃ¥
    0.60
     additional
    0.60
     nữa
    0.59
    Activations Density 0.052%

    No Known Activations