© 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. 44454
    Prev
    Next
    INDEX
    Explanations

    periods at the end of sentences

    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
    241
    -0.15
    _Tis
    -0.14
    cano
    -0.13
    _REF
    -0.13
     Sister
    -0.13
    <\/
    -0.12
    ueva
    -0.12
    -chan
    -0.12
    so
    -0.12
    ://
    -0.12
    POSITIVE LOGITS
    opis
    0.14
    .dispatcher
    0.14
    :convert
    0.13
    kw
    0.13
    uty
    0.12
    rophe
    0.12
    orz
    0.12
    acades
    0.12
    âķĿ
    0.12
    OA
    0.12
    Activations Density 0.008%

    No Known Activations