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. 23160
    Prev
    Next
    INDEX
    Explanations

    references to funding and grant opportunities related to community and economic development

    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
     Interior
    -0.16
    obra
    -0.16
    Interior
    -0.15
    /cards
    -0.15
    OfClass
    -0.14
     Fare
    -0.14
    807
    -0.14
    à¹Ĥà¸Ļ
    -0.14
    iban
    -0.14
    ugo
    -0.14
    POSITIVE LOGITS
     foundation
    0.20
     Ford
    0.20
     foundations
    0.19
     Soros
    0.17
     Fet
    0.17
    anker
    0.16
    ersh
    0.16
     Pew
    0.15
    Ford
    0.15
    ynchron
    0.15
    Activations Density 0.022%

    No Known Activations