© 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. 84290
    Prev
    Next
    INDEX
    Explanations

    references to COVID-19 and related medical scenarios

    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
     Hague
    -0.07
    éģĩ
    -0.07
    TIMER
    -0.07
    Msp
    -0.07
    áºŃu
    -0.07
    Gratis
    -0.07
    ái
    -0.07
    ichert
    -0.07
    .googlecode
    -0.07
    iliate
    -0.07
    POSITIVE LOGITS
     Delta
    0.07
     infected
    0.07
     died
    0.07
     delta
    0.07
     respir
    0.07
     ventil
    0.07
     die
    0.07
     Transmission
    0.06
     infect
    0.06
     vi
    0.06
    Activations Density 0.009%

    No Known Activations