© 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. 30045
    Prev
    Next
    INDEX
    Explanations

    references to occupations related to printing and lithography

    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
    ยาว
    -0.14
    Įĵ
    -0.14
     Builders
    -0.14
     Leon
    -0.13
     Logged
    -0.13
     Covered
    -0.13
     Instrument
    -0.13
     gesch
    -0.13
    .wav
    -0.13
    ÙĪص
    -0.13
    POSITIVE LOGITS
     printing
    0.60
     print
    0.52
     Printing
    0.50
     printers
    0.47
     printer
    0.46
    Printing
    0.45
    printing
    0.45
    -print
    0.45
     presses
    0.44
     Print
    0.43
    Activations Density 0.028%

    No Known Activations