© 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. 15-LLAMASCOPE-RES-131K
    11. 27457
    Prev
    Next
    INDEX
    Explanations

    phrases indicating changes, outcomes, or significant events related to public health

    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
     nackte
    -0.07
    ردÙĩ
    -0.06
    ела
    -0.06
     stripped
    -0.06
    _regularizer
    -0.06
    дейÑģÑĤв
    -0.06
    osa
    -0.06
    ERGY
    -0.06
     scri
    -0.06
    ystem
    -0.06
    POSITIVE LOGITS
     trend
    0.07
    erli
    0.07
     Trend
    0.06
    /Dk
    0.06
    HAS
    0.06
     Herbert
    0.06
     week
    0.06
    angep
    0.06
     tents
    0.06
    ennes
    0.06
    Activations Density 0.006%

    No Known Activations