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

    Neuronpedia

    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. 94580
    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
     rolling
    -0.07
    رÙĬع
    -0.06
     ground
    -0.06
    Äįek
    -0.06
     Rapid
    -0.06
     PGA
    -0.06
    å©
    -0.06
     golf
    -0.06
    çİ©
    -0.06
     íĶĮëłĪìĿ´
    -0.06
    POSITIVE LOGITS
     swim
    0.12
     swimming
    0.11
     Swimming
    0.11
     Swim
    0.10
     swims
    0.10
    æ³³
    0.10
     pisc
    0.09
    ewater
    0.09
     aquatic
    0.09
     Aqua
    0.09
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.