© 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. 43129
    Prev
    Next
    INDEX
    Explanations

    references to military activity and economic statistics

    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
    utut
    -0.15
    ANTE
    -0.15
    /xhtml
    -0.14
     ÙħÛĮÙĦادÛĮ
    -0.14
    orthand
    -0.14
    idis
    -0.14
    ITTE
    -0.14
    ideon
    -0.14
    าà¸į
    -0.14
    OnUiThread
    -0.13
    POSITIVE LOGITS
     last
    0.55
     during
    0.47
    last
    0.42
    during
    0.39
    à¹ĥà¸Ļà¸Ľ
    0.38
    Last
    0.37
     LAST
    0.35
     Last
    0.35
     During
    0.34
    _last
    0.34
    Activations Density 0.139%

    No Known Activations