© 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. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 15713
    Prev
    Next
    INDEX
    Explanations

    references to shopping cart elements and user media interaction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    710
    -0.06
    ovsky
    -0.06
    ine
    -0.06
     de
    -0.06
    jen
    -0.06
    verture
    -0.06
    ear
    -0.06
    ServerError
    -0.06
    ima
    -0.05
    à¥įवप
    -0.05
    POSITIVE LOGITS
     cart
    0.10
    cart
    0.08
    'gc
    0.08
    eyh
    0.07
    -cart
    0.07
     CART
    0.07
     Cart
    0.07
    CartItem
    0.07
    Cart
    0.07
    ransition
    0.07
    Activations Density 0.005%

    No Known Activations