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. 23507
    Prev
    Next
    INDEX
    Explanations

    questions about services and information related to local councils or police matters

    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
     perhaps
    -0.16
    .googlecode
    -0.15
    uxtap
    -0.15
     详æĥħ
    -0.14
     belki
    -0.14
     either
    -0.14
     possibly
    -0.14
    à¥Ģश
    -0.13
     شاÛĮد
    -0.13
    .scalablytyped
    -0.13
    POSITIVE LOGITS
    /my
    0.23
     my
    0.22
     myself
    0.21
    æĪij
    0.21
     saya
    0.20
     puedo
    0.20
    ç»ĻæĪij
    0.19
    æĪijçļĦ
    0.19
    ï¼ĮæĪij
    0.18
     meu
    0.18
    Activations Density 0.041%

    No Known Activations