© 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. 41058
    Prev
    Next
    INDEX
    Explanations

    references to herd immunity and public health strategies

    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
    HING
    -0.07
     гÑĸд
    -0.07
     kodu
    -0.07
    айд
    -0.07
    داد
    -0.07
    @api
    -0.07
    ÑĥÑĢи
    -0.06
     ROOT
    -0.06
    ysis
    -0.06
    رÛĮز
    -0.06
    POSITIVE LOGITS
     herd
    0.09
     transmission
    0.08
     population
    0.08
     community
    0.08
     Transmission
    0.08
     transmissions
    0.08
    Transmission
    0.07
    人人
    0.07
     circulation
    0.07
     collective
    0.07
    Activations Density 0.004%

    No Known Activations