© 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. 14733
    Prev
    Next
    INDEX
    Explanations

    references to recipes and cooking instructions

    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
    oxid
    -0.06
     wikipedia
    -0.06
    _decay
    -0.06
     Quiz
    -0.06
     fres
    -0.06
     Victor
    -0.06
    é²ľ
    -0.06
    иÑĩа
    -0.06
     brewed
    -0.05
    гов
    -0.05
    POSITIVE LOGITS
     recipes
    0.10
     recipe
    0.10
     ÑĢеÑĨеп
    0.07
     REC
    0.07
    recipe
    0.07
     Recipes
    0.07
    deniz
    0.07
     Recipe
    0.07
    loff
    0.07
     recip
    0.07
    Activations Density 0.021%

    No Known Activations