© 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. 24284
    Prev
    Next
    INDEX
    Explanations

    dates and numerical references related to schedules or timeframes

    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
    ourg
    -0.16
    ittel
    -0.15
    	Copyright
    -0.15
    itti
    -0.14
    зÑĭ
    -0.13
    .cm
    -0.13
    ritel
    -0.13
    ither
    -0.13
    annis
    -0.13
    oir
    -0.13
    POSITIVE LOGITS
    th
    0.23
    rd
    0.17
    nd
    0.16
    TH
    0.14
    ardin
    0.14
    epam
    0.14
    erse
    0.13
     weekend
    0.13
    T
    0.13
    st
    0.13
    Activations Density 0.045%

    No Known Activations