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

    Neuronpedia

    Jacobian LensNEW
    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. 14679
    Prev
    Next
    INDEX
    Explanations

    financial terminology related to bond markets and trading practices

    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
    ocha
    -0.15
    онÑĮ
    -0.14
     pinch
    -0.14
    els
    -0.14
    upertino
    -0.13
    eyim
    -0.13
    -js
    -0.13
    ague
    -0.13
     fare
    -0.13
    ضا
    -0.13
    POSITIVE LOGITS
     hed
    0.23
     instruments
    0.23
     Hed
    0.22
     Instruments
    0.22
     risk
    0.22
    hed
    0.19
     Participants
    0.19
     exposures
    0.19
     transactions
    0.19
     se
    0.19
    Activations Density 0.078%

    No Known Activations