© 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. 22407
    Prev
    Next
    INDEX
    Explanations

    numeric values, particularly related to time and measurements

    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
     Mills
    -0.18
     Milo
    -0.17
    -hours
    -0.17
    Mill
    -0.16
     Millennium
    -0.16
     mills
    -0.16
     Mill
    -0.16
    ิศ
    -0.15
    -hour
    -0.15
     Woche
    -0.15
    POSITIVE LOGITS
     minute
    0.69
     minutes
    0.64
    -minute
    0.59
     min
    0.56
    minute
    0.55
     Minute
    0.52
    min
    0.52
     Minutes
    0.50
    åĪĨéĴŁ
    0.50
    minutes
    0.49
    Activations Density 0.042%

    No Known Activations