© 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. 106524
    Prev
    Next
    INDEX
    Explanations

    instances of "he" or variations of "can" indicating ability or perception

    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
    äºĪ
    -0.07
    inka
    -0.07
    eking
    -0.07
     Kahn
    -0.06
    ",__
    -0.06
    .isAuthenticated
    -0.06
     DIRECTORY
    -0.06
    бÑĢа
    -0.06
    ohen
    -0.06
    ÙĢ
    -0.06
    POSITIVE LOGITS
     hear
    0.08
     see
    0.07
     Dun
    0.07
     heard
    0.07
     Hear
    0.06
    γÏĮ
    0.06
    hear
    0.06
    sil
    0.06
    see
    0.06
     ÑģлÑĭÑĪ
    0.06
    Activations Density 0.014%

    No Known Activations