© 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. 54105
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to ordering and reservations

    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
     Dud
    -0.15
    roke
    -0.15
    éĢīæĭ
    -0.15
    ogne
    -0.15
    heim
    -0.14
    acket
    -0.14
    /MPL
    -0.14
    ewe
    -0.14
    agem
    -0.14
    errick
    -0.14
    POSITIVE LOGITS
     deliver
    0.31
     delivered
    0.30
     ship
    0.29
     delivery
    0.27
     shipped
    0.26
     delivering
    0.25
     delivers
    0.25
    deliver
    0.24
     ships
    0.24
     Deliver
    0.23
    Activations Density 0.030%

    No Known Activations