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. 31315
    Prev
    Next
    INDEX
    Explanations

    mentions of government officials or government-related topics

    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
    er
    -0.16
    ibling
    -0.15
    .Java
    -0.15
    jos
    -0.15
    ibly
    -0.15
    eres
    -0.15
    ively
    -0.15
    edly
    -0.15
    ucz
    -0.15
    kil
    -0.14
    POSITIVE LOGITS
    t
    0.22
    ’t
    0.22
    't
    0.21
    ornment
    0.19
    enance
    0.18
    s
    0.18
    inda
    0.17
    vern
    0.16
    ä¹Ī
    0.16
    `t
    0.16
    Activations Density 0.004%

    No Known Activations