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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 23807
    Prev
    Next
    INDEX
    Explanations

    occurrences of numbers and references to attendee counts in events or gatherings

    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
    ATAL
    -0.15
    celik
    -0.15
    ivor
    -0.14
    æľĽ
    -0.14
    _WM
    -0.14
     jer
    -0.14
     Reeves
    -0.14
    票
    -0.13
     ä½IJ
    -0.13
    ibraries
    -0.13
    POSITIVE LOGITS
     show
    0.55
    show
    0.55
     showing
    0.53
     showed
    0.52
    -show
    0.51
     SHOW
    0.50
     shows
    0.50
     Show
    0.50
     Showing
    0.47
    SHOW
    0.47
    Activations Density 0.035%

    No Known Activations