© 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. 116360
    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
    sko
    -0.08
    ..↵↵↵↵
    -0.06
    adesh
    -0.06
    ofilm
    -0.06
    fel
    -0.06
     Moines
    -0.06
    ahun
    -0.06
    ifle
    -0.06
    drug
    -0.06
    andi
    -0.06
    POSITIVE LOGITS
    ³
    0.07
    _callbacks
    0.06
    خاÙĨ
    0.06
    ials
    0.06
     Buckingham
    0.06
    overe
    0.06
    inal
    0.06
    íģ
    0.06
    itty
    0.06
    MBProgressHUD
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.