© 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. 43508
    Prev
    Next
    INDEX
    Explanations

    negative terms related to financial and health declines

    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
    /write
    -0.18
    *width
    -0.17
    odore
    -0.17
     widely
    -0.16
    ag
    -0.16
    ):?>↵
    -0.16
     unw
    -0.16
    eur
    -0.16
    swire
    -0.16
    èħķ
    -0.16
    POSITIVE LOGITS
    efully
    0.21
    nesday
    0.21
    /month
    0.19
    bsite
    0.19
    owski
    0.19
    craft
    0.17
    fully
    0.17
    ows
    0.17
    aston
    0.17
    robe
    0.16
    Activations Density 0.001%

    No Known Activations