© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 31729
    Prev
    Next
    INDEX
    Explanations

    phrases related to public health crises and their consequences

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    Gatt
    -0.08
    zı
    -0.07
    ault
    -0.07
    InView
    -0.07
    ã
    -0.07
    еÑĢж
    -0.07
    ãģ«åĩº
    -0.06
    olor
    -0.06
     lesion
    -0.06
    _DISABLE
    -0.06
    POSITIVE LOGITS
     related
    0.07
    related
    0.06
     Tall
    0.06
     nackte
    0.06
    _related
    0.06
    Related
    0.06
    ioni
    0.06
    unya
    0.06
    -related
    0.05
     Reasons
    0.05
    Activations Density 0.027%

    No Known Activations