© 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. 25298
    Prev
    Next
    INDEX
    Explanations

    references to top-ranked sports prospects in recruitment 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
    exus
    -0.19
     Rao
    -0.17
     veter
    -0.16
     guild
    -0.16
    enler
    -0.16
    å°Ħ
    -0.16
     rookie
    -0.16
     stub
    -0.15
    âĻª
    -0.15
     Sez
    -0.15
    POSITIVE LOGITS
     commitments
    0.43
     commitment
    0.43
     commit
    0.41
     commits
    0.40
     Commit
    0.40
     committed
    0.39
     COMMIT
    0.38
    committed
    0.38
    commit
    0.37
    Commit
    0.35
    Activations Density 0.052%

    No Known Activations