© 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. 6006
    Prev
    Next
    INDEX
    Explanations

    references to the number of participants or capacity in a context

    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
    ogan
    -0.08
    inha
    -0.07
    ÃĹ↵↵
    -0.07
    âĢĮâĢĮ
    -0.06
    .addObject
    -0.06
    ocio
    -0.06
    ÑĸÑı
    -0.06
    bler
    -0.06
    Wer
    -0.06
     Moines
    -0.06
    POSITIVE LOGITS
    åºľ
    0.06
    621
    0.06
    ANGUAGE
    0.06
     shape
    0.06
    arih
    0.06
     barbecue
    0.06
    ENTION
    0.05
     Shape
    0.05
    bgcolor
    0.05
     Nicholson
    0.05
    Activations Density 0.000%

    No Known Activations