© 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. 41839
    Prev
    Next
    INDEX
    Explanations

    the preposition "at" in various contexts

    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
     voks
    -0.15
     erotik
    -0.13
    alim
    -0.13
     iParam
    -0.13
     onDataChange
    -0.12
    siz
    -0.12
     wireType
    -0.12
    é«ĺæ¸ħ
    -0.12
    ÑģпÑĸлÑĮ
    -0.12
     à¸Ľà¸£à¸°à¹Ģà¸Ĺศ
    -0.12
    POSITIVE LOGITS
    .deb
    0.13
     fran
    0.12
    Crud
    0.12
    552
    0.12
    ìĤ¬ì§Ģ
    0.12
     local
    0.12
    [sizeof
    0.12
    AFX
    0.12
    .GetData
    0.12
    isque
    0.11
    Activations Density 0.000%

    No Known Activations