© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Julius Han · Gated SAE for Llama3-8B-Instruct
    5. Llama3-8B-IT
    7. Residual Stream
    9. 25-RES-JH
    11. 15788
    Prev
    Next
    INDEX
    Explanations

    references to government institutions and media relationships

    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
    reff
    -0.17
    hart
    -0.16
    uien
    -0.16
     Æ°Æ¡ng
    -0.14
    -0.14
    onta
    -0.14
    æĿIJ
    -0.14
    anlı
    -0.13
    ulkan
    -0.13
    æŁľ
    -0.13
    POSITIVE LOGITS
     lack
    0.32
     Lack
    0.28
     lap
    0.25
    lack
    0.25
     mouth
    0.24
     sto
    0.24
     paid
    0.23
     pup
    0.22
     Mouth
    0.21
     cron
    0.21
    Activations Density 0.054%

    No Known Activations