© 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. 5-LLAMASCOPE-RES-131K
    11. 125717
    Prev
    Next
    INDEX
    Explanations

    instances of numerical values and mathematical symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    ureka
    -0.07
    èŃľ
    -0.07
    onse
    -0.07
     Libre
    -0.06
    ssi
    -0.06
     è©
    -0.06
    аÑĢÑĩ
    -0.06
    NetMessage
    -0.06
    etrain
    -0.06
    LogFile
    -0.06
    POSITIVE LOGITS
     splash
    0.07
    çķ¥
    0.06
    Splash
    0.06
     Splash
    0.06
    urga
    0.06
     Civil
    0.06
    ाà¤ĸ
    0.06
     Cover
    0.06
     spl
    0.05
    amps
    0.05
    Activations Density 0.000%

    No Known Activations