© 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. 43733
    Prev
    Next
    INDEX
    Explanations

    references to fighter statistics and rankings in the context of MMA

    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
    acula
    -0.17
    Æ°ng
    -0.16
    ateria
    -0.15
    avig
    -0.15
     tower
    -0.14
    atore
    -0.14
     ÐŁÐ¾Ðº
    -0.14
    erva
    -0.14
    ÙĦÛĮت
    -0.14
    ento
    -0.14
    POSITIVE LOGITS
     wel
    0.26
    uden
    0.19
    ãĥķãĤ
    0.18
     middle
    0.17
    .middle
    0.16
     Middle
    0.15
    Middle
    0.15
    BM
    0.15
    chsel
    0.15
    udur
    0.14
    Activations Density 0.013%

    No Known Activations