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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 17981
    Prev
    Next
    INDEX
    Explanations

    aspects related to food delivery services and digital ordering trends

    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
    ãĥĨãĤ£
    -0.07
     mun
    -0.07
    elow
    -0.07
    inline
    -0.06
     Mont
    -0.06
     pow
    -0.06
    ãĥ¼ãĥª
    -0.06
    æ£ļ
    -0.06
    vod
    -0.06
     mail
    -0.06
    POSITIVE LOGITS
     Ordering
    0.07
     orders
    0.07
    achu
    0.07
     ordering
    0.07
    fleet
    0.07
    orders
    0.07
     restaurant
    0.07
    едак
    0.07
    Ñĥнк
    0.07
     urb
    0.07
    Activations Density 0.024%

    No Known Activations