© 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. 18682
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ilo
    -0.08
    CharCode
    -0.07
    aleb
    -0.07
    nyder
    -0.07
    /fixtures
    -0.07
    خت
    -0.07
    /ay
    -0.07
    ittel
    -0.07
    ÙĪÛĮÙĦ
    -0.07
    ĮĢ
    -0.07
    POSITIVE LOGITS
    UME
    0.06
    .rt
    0.06
     seam
    0.06
    ë§ī
    0.05
    &amp
    0.05
    namen
    0.05
    üme
    0.05
     Fur
    0.05
    èħ
    0.05
    ↵
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.