Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Julius Han · Gated SAE for Llama3-8B-Instruct
    3. Llama3-8B-IT
    4. Residual Stream
    5. 25-RES-JH
    6. 23209
    Prev
    Next
    INDEX
    Explanations

    references to specific acts and scenes in literary works, particularly plays

    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
     COPYING
    -0.14
     CONTRIBUTORS
    -0.14
    á»Ļt
    -0.14
    ã
    -0.13
     bunch
    -0.13
     Essen
    -0.13
    ÃŃcia
    -0.13
     designer
    -0.13
     Há»ĵng
    -0.13
    ìĦłìĿĦ
    -0.12
    POSITIVE LOGITS
    _traits
    0.16
    .Slice
    0.16
    foil
    0.16
    elsius
    0.16
    aepernick
    0.16
    brid
    0.15
    lines
    0.15
    gettext
    0.15
    à¸ķà¸Ńà¸Ļ
    0.15
    phis
    0.14
    Activations Density 0.010%

    No Known Activations