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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 55046
    Prev
    Next
    INDEX
    Explanations

    references to the performance of the Lions' defense in relation to specific game situations and player actions

    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
    570
    -0.16
     cin
    -0.15
     Dol
    -0.15
    лÑĥÑĩ
    -0.15
    ovy
    -0.14
     padd
    -0.14
     masc
    -0.14
     Rupert
    -0.14
    iba
    -0.14
    aney
    -0.14
    POSITIVE LOGITS
     Lions
    0.33
     lions
    0.23
     Detroit
    0.22
    Staff
    0.22
     Lion
    0.21
     Stafford
    0.19
     lion
    0.19
    Detroit
    0.18
     Michigan
    0.17
    Michigan
    0.17
    Activations Density 0.018%

    No Known Activations