© 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
    2. Julius Han · Gated SAE for Llama3-8B-Instruct
    3. Llama3-8B-IT
    4. Residual Stream
    5. 25-RES-JH
    6. 28692
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and operational symbols

    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
    aat
    -0.15
     ¬
    -0.14
    --
    -0.13
    aan
    -0.13
    "
    -0.13
    aggi
    -0.13
     Yüz
    -0.13
    illet
    -0.13
    owie
    -0.13
     Pull
    -0.12
    POSITIVE LOGITS
    apgolly
    0.15
    SupportedContent
    0.14
    UILayout
    0.14
     :↵↵
    0.14
    ãĥ¼ãĤ¹ãĥĪ
    0.14
    öt
    0.14
    /XMLSchema
    0.13
    å͝
    0.13
    PostalCodes
    0.13
    DonaldTrump
    0.13
    Activations Density 0.250%

    No Known Activations