© 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. 21936
    Prev
    Next
    INDEX
    Explanations

    specific player names or related identifiers in a sports context

    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
    ocide
    -0.15
    utow
    -0.14
    itet
    -0.14
    vice
    -0.14
    รà¸Ńà¸ĩ
    -0.14
    èİ
    -0.13
     Robbins
    -0.13
    ãĥ¼ãĥª
    -0.13
     Convenience
    -0.13
    enne
    -0.13
    POSITIVE LOGITS
     EXTI
    0.15
    OMATIC
    0.14
    Ī
    0.14
     r
    0.14
    âĶĶ
    0.14
    ÏĢλα
    0.14
    MBED
    0.13
    모
    0.13
    aller
    0.13
     coh
    0.13
    Activations Density 0.012%

    No Known Activations