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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 40809
    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
    ùa
    -0.07
    Ư
    -0.07
    éIJ
    -0.07
    елеÑĦ
    -0.07
    irim
    -0.07
    _binding
    -0.07
    cury
    -0.07
    ÏĢÎŃ
    -0.07
    æĿ¡
    -0.07
    è¿Ļæł·çļĦ
    -0.07
    POSITIVE LOGITS
    aya
    0.07
    tring
    0.05
     Progress
    0.05
    :↵
    0.05
    tf
    0.05
     CONS
    0.05
    iate
    0.05
    igue
    0.05
     :↵
    0.05
     &↵
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.