© 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. 9-LLAMASCOPE-RES-131K
    11. 96381
    Prev
    Next
    INDEX
    Explanations

    phrases indicating additional details or features

    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
     pdb
    -0.07
    criptors
    -0.06
     Better
    -0.06
    omik
    -0.06
    æ£Ĵ
    -0.06
    ponder
    -0.06
    ë¹Ļ
    -0.06
     apar
    -0.06
    qui
    -0.05
     Awakening
    -0.05
    POSITIVE LOGITS
    ãģ¨ãģĦ
    0.07
     Kraj
    0.07
    astes
    0.07
    ãĥ
    0.07
     Bond
    0.07
     Mitar
    0.06
     Güven
    0.06
    ytt
    0.06
    Interop
    0.06
    allis
    0.06
    Activations Density 0.010%

    No Known Activations