© 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. 9-LLAMASCOPE-RES-131K
    11. 97445
    Prev
    Next
    INDEX
    Explanations

    references to COVID-19 restrictions and related public health measures

    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
     CO
    -0.06
     Shrine
    -0.06
    ibold
    -0.06
    ãĥ¼ãĥ«ãĥī
    -0.06
    CO
    -0.06
     Nem
    -0.06
     Stra
    -0.06
     Freund
    -0.06
     multip
    -0.06
     Colo
    -0.06
    POSITIVE LOGITS
    ondon
    0.08
    vio
    0.07
    .uk
    0.07
    WN
    0.07
     درÛĮ
    0.07
    ayas
    0.06
    424
    0.06
    DataService
    0.06
    ãģ§ãĤĤ
    0.06
    Ä°ng
    0.06
    Activations Density 0.013%

    No Known Activations