© 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. 18705
    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
    üme
    -0.07
    .pattern
    -0.07
    HSV
    -0.06
    lam
    -0.06
    ials
    -0.06
    wa
    -0.06
     Wa
    -0.06
    ises
    -0.06
    .gc
    -0.06
     unpopular
    -0.06
    POSITIVE LOGITS
     hete
    0.07
    hammer
    0.07
    izza
    0.07
     CACHE
    0.06
    mand
    0.06
    екÑģи
    0.06
    ash
    0.06
    олож
    0.06
    764
    0.06
    erece
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.