© 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
    3. Julius Han · Gated SAE for Llama3-8B-Instruct
    5. Llama3-8B-IT
    7. Residual Stream
    9. 25-RES-JH
    11. 24351
    Prev
    Next
    INDEX
    Explanations

    numerical values related to time, specifically referencing dates and durations

    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
    à¤ľà¤¨
    -0.15
    eness
    -0.15
    ãĥ¼
    -0.15
    ancel
    -0.15
    ÙĤات
    -0.15
    kelas
    -0.14
    ë¡ł
    -0.14
    bons
    -0.14
    oeff
    -0.14
        ↵    ↵
    -0.14
    POSITIVE LOGITS
    ãģ°
    0.16
     Rockefeller
    0.16
    orsi
    0.16
    áj
    0.16
    ήÏĤ
    0.16
    oggler
    0.15
    aucoup
    0.15
    omez
    0.15
    ìĸ¸
    0.15
    anje
    0.15
    Activations Density 0.050%

    No Known Activations