© 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. 9-LLAMASCOPE-RES-131K
    11. 96431
    Prev
    Next
    INDEX
    Explanations

    phrases related to food, particularly ones that describe ingredients or recipes

    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
    lse
    -0.07
     Dalton
    -0.07
     Tur
    -0.07
    аÑĢÑı
    -0.06
     premise
    -0.06
    atis
    -0.06
    rong
    -0.06
    473
    -0.06
    642
    -0.06
     U
    -0.05
    POSITIVE LOGITS
    žen
    0.07
     omas
    0.07
     sẵn
    0.07
    浩
    0.07
    kovi
    0.07
    INED
    0.07
    à¤łà¤¨
    0.07
    isher
    0.07
    .asm
    0.06
     bras
    0.06
    Activations Density 0.076%

    No Known Activations