© 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. 13535
    Prev
    Next
    INDEX
    Explanations

    references to the letter "K" as a standalone letter or 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
    اÙĨ
    -0.20
    ÑĢÑĸм
    -0.18
    =$("#
    -0.18
    à¤Ī
    -0.17
    gebra
    -0.17
    он
    -0.16
    onta
    -0.16
    оÑģÑĤ
    -0.16
    ÑĥÑĢ
    -0.16
    yle
    -0.15
    POSITIVE LOGITS
    ean
    0.23
    ev
    0.23
    t
    0.22
    ow
    0.19
    bler
    0.19
    eh
    0.19
    ik
    0.19
    eb
    0.19
    haled
    0.17
    ees
    0.17
    Activations Density 0.046%

    No Known Activations