© 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. 5881
    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
     proh
    -0.07
    jas
    -0.06
    åķ
    -0.06
     +=↵
    -0.06
    kiye
    -0.06
     recep
    -0.06
    Ê
    -0.06
     ê°Ļëĭ¤
    -0.06
     mov
    -0.06
    \Configuration
    -0.06
    POSITIVE LOGITS
    yny
    0.07
     GURL
    0.07
     instagram
    0.07
    ocket
    0.07
     FactoryGirl
    0.07
    epar
    0.06
    ieres
    0.06
     kì
    0.06
    odox
    0.06
    abet
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.