© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 58417
    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
    Not in Any Lists

    No Comments

    Negative Logits
     Michigan
    -0.08
     Indiana
    -0.07
    Michigan
    -0.07
     Traverse
    -0.06
    Indiana
    -0.06
    å·¡
    -0.06
     USA
    -0.06
    taÅŁ
    -0.06
     Colorado
    -0.06
     âĢª
    -0.06
    POSITIVE LOGITS
     Hong
    0.13
    Hong
    0.10
     HK
    0.09
    atri
    0.08
     é¦Ļ港
    0.08
     hk
    0.07
     Ernst
    0.07
     island
    0.07
    é¦Ļ港
    0.07
     Wong
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.