© 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. 63005
    Prev
    Next
    INDEX
    Explanations

    intensifiers that express strong affirmation or approval

    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
    ulfilled
    -0.10
    arde
    -0.07
    ispers
    -0.07
    ockets
    -0.07
    orama
    -0.07
    rick
    -0.07
    ardin
    -0.07
     imageSize
    -0.07
    istrovstvÃŃ
    -0.07
    olland
    -0.07
    POSITIVE LOGITS
    olutely
    0.07
     nothing
    0.07
    -ÑĤаки
    0.07
    mente
    0.07
    ively
    0.07
     positively
    0.06
    utely
    0.06
     absolutely
    0.06
    ments
    0.06
    ElementsBy
    0.06
    Activations Density 0.006%

    No Known Activations