© 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. 38899
    Prev
    Next
    INDEX
    Explanations

    phrases related to intellectual property and its impact on access to resources 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
    kir
    -0.10
    .gf
    -0.08
    ackers
    -0.08
    Ỽ
    -0.07
    isque
    -0.07
    äºľ
    -0.07
    /Dk
    -0.07
    (compact
    -0.07
     докÑĥменÑĤа
    -0.07
    etu
    -0.07
    POSITIVE LOGITS
     temporarily
    0.09
     wa
    0.08
    ormal
    0.07
     relief
    0.07
     extensions
    0.07
     temporary
    0.07
    temp
    0.07
     extension
    0.07
     Extensions
    0.07
     вÑĢем
    0.07
    Activations Density 0.003%

    No Known Activations