© 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. 9-LLAMASCOPE-RES-131K
    11. 97873
    Prev
    Next
    INDEX
    Explanations

    references to mayonnaise

    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
    ancia
    -0.07
    kan
    -0.06
    ằ
    -0.06
    arshal
    -0.06
    787
    -0.06
    kov
    -0.06
    471
    -0.06
     Pom
    -0.06
     Trou
    -0.06
    ulen
    -0.06
    POSITIVE LOGITS
    ayers
    0.07
    onders
    0.07
    seau
    0.07
    ourt
    0.07
    TRL
    0.07
    аÑĢÑĮ
    0.07
    ios
    0.06
    iners
    0.06
    carousel
    0.06
    INESS
    0.06
    Activations Density 0.012%

    No Known Activations