© 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. 89671
    Prev
    Next
    INDEX
    Explanations

    terms related to geographical measurements or coordinates

    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
    Æ°á»Ŀi
    -0.08
    CEED
    -0.07
    askell
    -0.07
    rossover
    -0.07
    warnings
    -0.07
    ÑĨеп
    -0.07
     ”↵↵
    -0.07
    ساÙĦ
    -0.07
     å·Ŀ
    -0.07
    ERV
    -0.06
    POSITIVE LOGITS
     distance
    0.09
    distance
    0.08
     Distance
    0.07
    Distance
    0.07
     distances
    0.07
    nick
    0.07
    orest
    0.06
     ÑĢаÑģÑģÑĤоÑı
    0.06
    isset
    0.06
     ëĸ¨ìĸ´
    0.06
    Activations Density 0.002%

    No Known Activations