© 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. 25198
    Prev
    Next
    INDEX
    Explanations

    phrases indicating duration or time-related metrics

    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
     Weeks
    -0.24
     Days
    -0.20
    Week
    -0.19
    Days
    -0.19
    weeks
    -0.18
     Fifty
    -0.18
     fortn
    -0.18
    86
    -0.17
     Forty
    -0.17
     Thirty
    -0.17
    POSITIVE LOGITS
     decade
    0.61
     years
    0.56
     five
    0.56
     Years
    0.47
     ten
    0.46
    Years
    0.45
    years
    0.43
     seven
    0.42
    ä¸īå¹´
    0.42
     YEARS
    0.41
    Activations Density 0.102%

    No Known Activations