© 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. 121388
    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
    clipse
    -0.06
    unders
    -0.06
    enade
    -0.06
    Ñijм
    -0.06
    Carthy
    -0.06
     Ãĸr
    -0.06
     Murdoch
    -0.06
    ør
    -0.06
    (åľŁ
    -0.06
    annah
    -0.06
    POSITIVE LOGITS
    ầm
    0.07
     Laz
    0.06
    iele
    0.06
    iales
    0.06
    ulumi
    0.06
    ë°
    0.06
     kinds
    0.06
    ãģķãģ¾
    0.06
     And
    0.06
     locals
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.