© 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. 28378
    Prev
    Next
    INDEX
    Explanations

    pricing information and promotional offers in products

    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
    ajo
    -0.16
     priced
    -0.15
     Tucker
    -0.15
    .asset
    -0.14
     Batch
    -0.14
     Tickets
    -0.14
    rossover
    -0.13
    etter
    -0.13
    dro
    -0.13
    Tickets
    -0.13
    POSITIVE LOGITS
     shipping
    0.56
     Shipping
    0.48
    shipping
    0.45
    Shipping
    0.44
     SHIPPING
    0.38
     delivery
    0.34
     shipped
    0.33
     ship
    0.33
     free
    0.32
    .ship
    0.31
    Activations Density 0.039%

    No Known Activations