© 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 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. 87657
    Prev
    Next
    INDEX
    Explanations

    references to calorie counts and nutritional information

    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
    ibu
    -0.07
    069
    -0.06
     nose
    -0.06
    .plugins
    -0.06
    uku
    -0.06
     fu
    -0.06
    æĹ
    -0.06
    abet
    -0.06
    awah
    -0.06
     triple
    -0.06
    POSITIVE LOGITS
    erne
    0.07
     اÙĦعÙĨ
    0.07
    oday
    0.06
     Hogan
    0.06
     Berm
    0.06
    å±ķ
    0.06
     Bolt
    0.06
    лаг
    0.06
     Alert
    0.06
     mili
    0.06
    Activations Density 0.001%

    No Known Activations