© 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. 12722
    Prev
    Next
    INDEX
    Explanations

    statistics related to player performance in sports

    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
    ikt
    -0.15
    !=(
    -0.14
     Ãľn
    -0.14
    تÙĩÙħ
    -0.13
    quan
    -0.13
    MOVED
    -0.13
    rawer
    -0.13
     Deb
    -0.12
    Ļ
    -0.12
     fragmented
    -0.12
    POSITIVE LOGITS
     ERA
    0.25
    ERA
    0.24
     earned
    0.20
    era
    0.19
     Earn
    0.17
    eras
    0.16
    -INF
    0.15
    uchs
    0.15
    orra
    0.15
    amura
    0.15
    Activations Density 0.019%

    No Known Activations