© 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. 17-LLAMASCOPE-RES-131K
    11. 125034
    Prev
    Next
    INDEX
    Explanations

    references to masks and related behaviors during the COVID-19 pandemic

    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
    ipi
    -0.08
    ifton
    -0.07
    dif
    -0.07
     sitcom
    -0.06
    oy
    -0.06
    oins
    -0.06
    essed
    -0.06
    atto
    -0.06
    ilk
    -0.06
    rieve
    -0.06
    POSITIVE LOGITS
     mask
    0.22
     masks
    0.21
     Masks
    0.20
     Mask
    0.19
    -mask
    0.19
     MASK
    0.17
    Mask
    0.17
    mask
    0.16
    .mask
    0.16
     masked
    0.16
    Activations Density 0.060%

    No Known Activations