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. 23741
    Prev
    Next
    INDEX
    Explanations

    references to the automotive industry

    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
    /MPL
    -0.18
    lama
    -0.17
    лÑıн
    -0.17
    .scalablytyped
    -0.15
    ¯u
    -0.15
    isan
    -0.15
    erts
    -0.15
    rist
    -0.14
    KT
    -0.14
    /Area
    -0.14
    POSITIVE LOGITS
     parts
    0.24
     Parts
    0.22
     industry
    0.22
    -parts
    0.21
    Parts
    0.21
    _parts
    0.18
    parts
    0.18
    industry
    0.17
     Industry
    0.17
    /auto
    0.17
    Activations Density 0.017%

    No Known Activations