© 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. 6015
    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
    esser
    -0.08
    eum
    -0.08
    oldem
    -0.07
    unct
    -0.07
    Ĭ
    -0.07
    ernote
    -0.07
    foon
    -0.07
    Ùijد
    -0.07
    swer
    -0.07
    etch
    -0.07
    POSITIVE LOGITS
    xes
    0.06
     traffic
    0.06
    mass
    0.06
     Franklin
    0.06
     mass
    0.06
    Attr
    0.06
     unle
    0.05
     you
    0.05
     Traffic
    0.05
    102
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.