© 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. 15-LLAMASCOPE-RES-131K
    11. 86141
    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
    IBOutlet
    -0.07
    emmel
    -0.07
    antan
    -0.06
    ivant
    -0.06
    asto
    -0.06
    amura
    -0.06
    pha
    -0.06
    ayscale
    -0.06
    istance
    -0.06
    .infinity
    -0.06
    POSITIVE LOGITS
    holm
    0.08
     sal
    0.07
     Sal
    0.07
     sur
    0.07
    _HC
    0.06
    olean
    0.06
    429
    0.06
    agua
    0.06
    vero
    0.06
     flo
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.