© 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. 96191
    Prev
    Next
    INDEX
    Explanations

    phrases indicating exceptions or conditions

    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
    728
    -0.07
    EDIUM
    -0.07
    èĨ
    -0.07
    multipart
    -0.07
    agoon
    -0.07
    noteq
    -0.06
    atron
    -0.06
     Vir
    -0.06
    ungan
    -0.06
    aÄŁ
    -0.06
    POSITIVE LOGITS
     historical
    0.07
     Historical
    0.07
     Mei
    0.07
    elsen
    0.06
     outright
    0.06
     indexer
    0.06
    oug
    0.06
     Stard
    0.06
     pq
    0.06
     identity
    0.06
    Activations Density 0.000%

    No Known Activations