© 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. 21649
    Prev
    Next
    INDEX
    Explanations

    references to sports leagues and their players, particularly in the context of protests or activism

    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
    еÑİ
    -0.15
    ngth
    -0.15
    访
    -0.14
    ÑģÑĤеÑĢ
    -0.14
    گاÙĩÛĮ
    -0.14
    λη
    -0.14
    ccione
    -0.14
    InView
    -0.14
     belki
    -0.13
    alion
    -0.13
    POSITIVE LOGITS
     either
    0.29
     already
    0.27
     expressed
    0.25
     express
    0.25
    either
    0.24
     have
    0.24
    Express
    0.23
     Express
    0.22
     Either
    0.22
     expresses
    0.22
    Activations Density 0.193%

    No Known Activations