© 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. 1354
    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
     latest
    -0.07
     helm
    -0.07
     state
    -0.06
     status
    -0.06
    laden
    -0.06
    plet
    -0.06
     Maid
    -0.06
    شار
    -0.05
    945
    -0.05
     Till
    -0.05
    POSITIVE LOGITS
    geber
    0.09
    iners
    0.07
    UBL
    0.07
    kke
    0.07
    .heroku
    0.07
    WithType
    0.07
    gesi
    0.07
    taÅŁ
    0.07
    onn
    0.07
    arness
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.