© 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. 9-LLAMASCOPE-RES-131K
    11. 94194
    Prev
    Next
    INDEX
    Explanations

    adjectives and descriptive phrases related to flavor and texture in food

    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
    uisse
    -0.07
    uth
    -0.07
    outh
    -0.07
    ifs
    -0.07
    .ms
    -0.07
    'er
    -0.07
    èmes
    -0.07
    expects
    -0.07
    euillez
    -0.07
    elong
    -0.07
    POSITIVE LOGITS
     "-//
    0.07
     Micha
    0.06
    ä¼į
    0.06
    ì¹ĺ를
    0.06
    aload
    0.06
     ÑĢазÑĸ
    0.06
    ÙĦاÙĦ
    0.06
     Fres
    0.06
    æŶåĢĻ
    0.06
     Reyn
    0.06
    Activations Density 0.002%

    No Known Activations