© 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
    3. Julius Han · Gated SAE for Llama3-8B-Instruct
    5. Llama3-8B-IT
    7. Residual Stream
    9. 25-RES-JH
    11. 43153
    Prev
    Next
    INDEX
    Explanations

    occurrences of numerical data and statistics related to games, teams, and competitions

    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
     many
    -0.19
     MUCH
    -0.18
     much
    -0.18
    much
    -0.18
     several
    -0.17
    许å¤ļ
    -0.17
     Several
    -0.17
     Many
    -0.16
    Much
    -0.16
     muchas
    -0.16
    POSITIVE LOGITS
     ÑħоÑĤÑı
    0.33
     either
    0.32
     atleast
    0.31
    èĩ³å°ij
    0.31
     alespoÅĪ
    0.30
     EITHER
    0.28
     least
    0.26
    either
    0.26
     âī¥
    0.26
     fewer
    0.24
    Activations Density 0.142%

    No Known Activations