© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 55370
    Prev
    Next
    INDEX
    Explanations

    opinions and evaluations regarding players 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
     Xxx
    -0.15
    å·±
    -0.14
     damer
    -0.13
    chein
    -0.13
     accessor
    -0.13
    iteli
    -0.13
    ÑĥÑģÑĤа
    -0.13
     bla
    -0.13
    ắp
    -0.12
     när
    -0.12
    POSITIVE LOGITS
     here
    0.17
     defaulted
    0.16
     intrig
    0.15
     MAY
    0.14
     slot
    0.14
     slight
    0.14
     probably
    0.14
    *this
    0.14
     instincts
    0.13
    ici
    0.13
    Activations Density 0.314%

    No Known Activations