© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 21203
    Prev
    Next
    INDEX
    Explanations

    phrases related to sporting events and game statistics

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
     many
    -0.19
     certain
    -0.18
     Many
    -0.16
    Many
    -0.16
    ourn
    -0.15
    -many
    -0.15
     MANY
    -0.15
    å¾Īå¤ļ
    -0.15
     Certain
    -0.15
    许å¤ļ
    -0.14
    POSITIVE LOGITS
     each
    0.38
     twice
    0.37
    åĪĨåĪ«
    0.37
    each
    0.36
    ä¸Ģ次
    0.32
     Twice
    0.31
     Each
    0.29
     once
    0.29
     EACH
    0.28
    Each
    0.27
    Activations Density 0.040%

    No Known Activations