© 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. 14078
    Prev
    Next
    INDEX
    Explanations

    references to statistics and performance metrics in sports

    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
    Äįer
    -0.17
    ajar
    -0.17
    ä¸Ģ次
    -0.15
    itti
    -0.15
     muster
    -0.15
    _INCREF
    -0.15
     Third
    -0.14
    ä½³
    -0.14
    以ä¸Ĭ
    -0.14
    ivated
    -0.14
    POSITIVE LOGITS
     first
    0.31
     last
    0.31
     next
    0.29
     remaining
    0.28
    first
    0.24
    last
    0.24
    remaining
    0.23
    next
    0.21
     ersten
    0.20
     letzten
    0.20
    Activations Density 0.036%

    No Known Activations