© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Julius Han · Gated SAE for Llama3-8B-Instruct
    3. Llama3-8B-IT
    4. Residual Stream
    5. 25-RES-JH
    6. 28218
    Prev
    Next
    INDEX
    Explanations

    phrases related to transfer and player movement in sports 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
     Vermont
    -0.18
     Minnesota
    -0.18
     Nevada
    -0.16
     Arizona
    -0.16
     Louisiana
    -0.15
     Florida
    -0.15
     Tennessee
    -0.15
    currentColor
    -0.15
    Minnesota
    -0.15
     Arkansas
    -0.15
    POSITIVE LOGITS
     Blacks
    0.26
     Morg
    0.23
     Pull
    0.22
     Norman
    0.21
    Pull
    0.19
     Bloom
    0.18
     Lub
    0.18
     Stark
    0.18
    ITH
    0.17
     campus
    0.17
    Activations Density 0.035%

    No Known Activations