© 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. 80871
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to language and dialects

    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
    crest
    -0.08
    Languages
    -0.07
    (æľ¨
    -0.07
     translation
    -0.07
     Languages
    -0.07
    translated
    -0.07
    addon
    -0.07
    gni
    -0.07
    oque
    -0.07
    conde
    -0.07
    POSITIVE LOGITS
     regional
    0.10
     Regional
    0.07
     dialect
    0.07
    Regional
    0.07
     variants
    0.06
     region
    0.06
     morph
    0.06
    var
    0.06
     dia
    0.06
     Modern
    0.06
    Activations Density 0.013%

    No Known Activations