© 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. 96004
    Prev
    Next
    INDEX
    Explanations

    expressions of desire and wants in various contexts

    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
    ine
    -0.06
     اÙĦÙħÙģ
    -0.06
    ale
    -0.06
     fare
    -0.06
    born
    -0.06
    erç
    -0.06
    que
    -0.06
    ilent
    -0.06
    ADO
    -0.06
    ally
    -0.06
    POSITIVE LOGITS
    ikat
    0.08
     acquisitions
    0.07
     unavailable
    0.07
     scarc
    0.07
     attain
    0.07
     acquisition
    0.07
     attainment
    0.07
    ogene
    0.07
     polož
    0.07
     elusive
    0.06
    Activations Density 0.020%

    No Known Activations