© 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. 15-LLAMASCOPE-RES-131K
    11. 87882
    Prev
    Next
    INDEX
    Explanations

    various symbols and operators commonly used in programming or markup contexts

    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
    omba
    -0.07
     latter
    -0.07
    ily
    -0.07
    ly
    -0.07
    ÑĥÑĤи
    -0.07
    è¾¼ãģ¿
    -0.07
    .idea
    -0.07
    _Api
    -0.07
    cps
    -0.07
    ilies
    -0.07
    POSITIVE LOGITS
    gli
    0.06
    istics
    0.06
     Fowler
    0.05
    ï¸ı
    0.05
    pa
    0.05
     Fro
    0.05
    aver
    0.05
    asc
    0.05
     central
    0.05
    кÑĢа
    0.05
    Activations Density 0.015%

    No Known Activations