© 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. 54374
    Prev
    Next
    INDEX
    Explanations

    punctuation and specific keywords related to documentation structure

    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
    ohl
    -0.17
    asics
    -0.16
    ãĤĪãģ³
    -0.14
    etto
    -0.14
    uzzi
    -0.14
    uze
    -0.14
     ><?
    -0.14
    ŀ
    -0.14
    errupt
    -0.14
    ãģ¯ãģļ
    -0.14
    POSITIVE LOGITS
     напÑĢимеÑĢ
    0.59
    ä¾ĭå¦Ĥ
    0.56
     ÙħØ«ÙĦا
    0.53
     example
    0.53
     ÐĿапÑĢимеÑĢ
    0.51
     napÅĻÃŃklad
    0.47
     For
    0.45
     ÃĸrneÄŁin
    0.44
     напÑĢиклад
    0.44
     eg
    0.42
    Activations Density 0.132%

    No Known Activations