© 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. 31578
    Prev
    Next
    INDEX
    Explanations

    references to "the" indicating emphasis on specific subjects or entities discussed in the text

    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
    oldur
    -0.07
    éģĹ
    -0.06
     stag
    -0.06
    ime
    -0.06
     одне
    -0.06
    è«ĩ
    -0.06
     irresist
    -0.06
    .compile
    -0.06
    aginator
    -0.06
    jay
    -0.06
    POSITIVE LOGITS
    rut
    0.08
    ApiClient
    0.07
     blame
    0.07
    人ãģ¯
    0.07
    .charCodeAt
    0.07
    ĨĴ
    0.07
    ÃŃÅ¡
    0.07
    uttle
    0.06
    .rawValue
    0.06
    à¹ģà¸Ļ
    0.06
    Activations Density 0.030%

    No Known Activations