© 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. 15481
    Prev
    Next
    INDEX
    Explanations

    phrases related to fitness and well-being

    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
    æ³ī
    -0.13
    ech
    -0.12
    :UITableView
    -0.12
    wald
    -0.12
    749
    -0.12
    isman
    -0.12
    äft
    -0.12
    еÑĤÑĮ
    -0.12
    attern
    -0.12
     snap
    -0.12
    POSITIVE LOGITS
     journey
    0.83
     Journey
    0.66
    jour
    0.65
     journeys
    0.57
    ourney
    0.46
     voyage
    0.45
     jour
    0.42
     path
    0.40
     od
    0.36
     trip
    0.35
    Activations Density 0.032%

    No Known Activations