© 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 EvalsExportsinterp-engineNEWAPI 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. 22545
    Prev
    Next
    INDEX
    Explanations

    terms related to NULL values and database concepts

    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¸Ļ
    -0.21
     latter
    -0.19
    intosh
    -0.18
    ا
    -0.17
    e
    -0.16
    Ø©
    -0.16
    ção
    -0.16
    al
    -0.16
    ancy
    -0.15
    stin
    -0.15
    POSITIVE LOGITS
    ÂĢÂĻ
    0.18
    /-
    0.17
     ÑģобоÑİ
    0.16
    .au
    0.15
    etheless
    0.15
    si
    0.14
    0.14
    spir
    0.14
    atre
    0.14
    ìĿ´ëĵľ
    0.13
    Activations Density 0.121%

    No Known Activations