© 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. 42604
    Prev
    Next
    INDEX
    Explanations

    phrases indicating uncertainty or skepticism

    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
     ex
    -0.18
     patch
    -0.15
    ignon
    -0.14
    428
    -0.14
     Patch
    -0.14
    HITE
    -0.14
    ights
    -0.14
     reck
    -0.14
    .ibatis
    -0.14
     la
    -0.14
    POSITIVE LOGITS
    ë°Ģ
    0.17
    geç
    0.15
    QA
    0.15
     fisse
    0.14
    ascimento
    0.14
     Raq
    0.14
    à¸Ļà¸Ķ
    0.14
     Alone
    0.14
    alone
    0.14
    qa
    0.14
    Activations Density 0.019%

    No Known Activations