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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 13089
    Prev
    Next
    INDEX
    Explanations

    the preposition "of"

    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
    ãĤĪãģĨãģª
    -0.20
    大
    -0.19
    ãĤĪãģĨãģ«
    -0.18
    à¸ľ
    -0.17
    ä¸Ģ
    -0.17
    ä¸ĢåĪĩ
    -0.17
    ä¸ĢçĤ¹
    -0.15
    umber
    -0.15
    abay
    -0.14
    ä¸ĢäºĽ
    -0.14
    POSITIVE LOGITS
     sorts
    0.36
    course
    0.31
     course
    0.31
    icina
    0.25
    lox
    0.24
    sted
    0.24
    ft
    0.23
    iciálnÃŃ
    0.22
    ï
    0.22
    icers
    0.22
    Activations Density 0.026%

    No Known Activations