© 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 EvalsExportsinterp-engineNEWAPI 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. 13914
    Prev
    Next
    INDEX
    Explanations

    terms related to financial distress and mortgage-related matters

    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
    ynet
    -0.16
    erva
    -0.16
     Barg
    -0.14
    lush
    -0.14
    nech
    -0.14
    å¶
    -0.14
    zia
    -0.13
    ibo
    -0.13
     PartialView
    -0.13
    ERM
    -0.13
    POSITIVE LOGITS
     refin
    0.25
     bor
    0.25
     Bor
    0.24
     max
    0.23
     mort
    0.23
     borrowed
    0.23
    borrow
    0.21
    bor
    0.21
     borrow
    0.21
    default
    0.21
    Activations Density 0.048%

    No Known Activations