© 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. 14350
    Prev
    Next
    INDEX
    Explanations

    elements that describe musical genres and their characteristics

    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
     Ending
    -0.07
     opening
    -0.06
    strup
    -0.06
    วà¸Ļ
    -0.06
    lich
    -0.06
     ÑĢÑĥк
    -0.06
     ending
    -0.06
     Bravo
    -0.06
    ·
    -0.06
     Opening
    -0.06
    POSITIVE LOGITS
    .strict
    0.07
    741
    0.07
     boom
    0.07
     ÐĴоз
    0.07
     styles
    0.07
    wave
    0.07
     scrut
    0.07
     Styles
    0.06
    493
    0.06
    Strict
    0.06
    Activations Density 0.010%

    No Known Activations