© 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. 89510
    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
    Not in Any Lists

    No Comments

    Negative Logits
     Tamil
    -0.07
     Shank
    -0.06
     Rohing
    -0.06
     Eston
    -0.06
    ãĥ³ãĤ¬
    -0.06
    myModal
    -0.06
     Kashmir
    -0.06
    ακ
    -0.06
    hest
    -0.06
     ÙħسÙĦÙħاÙĨ
    -0.06
    POSITIVE LOGITS
     Egypt
    0.16
    Egypt
    0.15
     Nile
    0.15
     Egyptian
    0.14
     Cairo
    0.14
     Egyptians
    0.14
     Ùħصر
    0.12
     Mısır
    0.11
    Kansas
    0.11
     cairo
    0.10
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.