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

    Neuronpedia

    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. 63903
    Prev
    Next
    INDEX
    Explanations

    phrases related to environmental statistics and projections

    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
    yles
    -0.14
     Fallon
    -0.14
    iale
    -0.13
    ÙħÙĨد
    -0.13
    lyph
    -0.12
    .scalablytyped
    -0.12
    /***************************************************************************↵
    -0.12
    eref
    -0.12
    avana
    -0.12
    ãĥ«ãĥķ
    -0.12
    POSITIVE LOGITS
     forecast
    0.75
     prediction
    0.71
     predictions
    0.71
     predicted
    0.70
     projection
    0.64
     predicts
    0.64
     projections
    0.63
     forecasts
    0.63
    forecast
    0.62
     Prediction
    0.61
    Activations Density 0.068%

    No Known Activations