© 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. 98136
    Prev
    Next
    INDEX
    Explanations

    references to COVID-19 testing and related processes

    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
    oya
    -0.07
    .gnu
    -0.07
     interesse
    -0.07
    UTES
    -0.07
    anders
    -0.07
    ियत
    -0.07
     blaze
    -0.07
    vel
    -0.06
     ped
    -0.06
    kee
    -0.06
    POSITIVE LOGITS
    icari
    0.06
     contempor
    0.06
    _SB
    0.06
     Hob
    0.06
    iture
    0.06
    brero
    0.05
     неÑĢ
    0.05
     Kendall
    0.05
    axed
    0.05
    .realpath
    0.05
    Activations Density 0.003%

    No Known Activations