© 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. 42646
    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
     Ernst
    -0.07
    \Id
    -0.07
    Å¡et
    -0.07
    elan
    -0.06
    eydi
    -0.06
    ctal
    -0.06
    evin
    -0.06
    ERIC
    -0.06
    CRET
    -0.06
    ietet
    -0.06
    POSITIVE LOGITS
    vig
    0.08
    648
    0.07
     Classes
    0.07
    797
    0.06
    ,System
    0.06
    ivery
    0.06
    е
    0.06
     Vig
    0.06
     vigil
    0.06
    stown
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.