© 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 EvalsExportsAPI 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. 56227
    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
    aterno
    -0.07
    .scalablytyped
    -0.07
     sca
    -0.07
    amo
    -0.07
    -regexp
    -0.07
    amba
    -0.07
     Sanayi
    -0.07
    å»
    -0.07
    isten
    -0.07
    ertino
    -0.07
    POSITIVE LOGITS
    tring
    0.06
     prost
    0.06
     âĢĮ
    0.06
    âĢį
    0.06
    onet
    0.06
    ø
    0.06
     Coch
    0.05
    ðŁ
    0.05
     Boeh
    0.05
     cann
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.