© 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. 63045
    Prev
    Next
    INDEX
    Explanations

    emotional expressions and personal experiences

    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
    ãĤ«ãĥĨ
    -0.08
    ẻ
    -0.08
    ÐĴаж
    -0.07
    ruba
    -0.07
    GLOSS
    -0.07
    оÑĢом
    -0.07
    ÐĦ
    -0.07
    ëĵľë¦¬
    -0.07
     rá»Ŀi
    -0.07
    iên
    -0.07
    POSITIVE LOGITS
    quot
    0.08
    isque
    0.07
    в
    0.06
    ..↵
    0.06
     dating
    0.06
    alar
    0.06
     Essay
    0.06
    istrovstvÃŃ
    0.06
    Sep
    0.06
    illis
    0.05
    Activations Density 1.936%

    No Known Activations