© 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. 17-LLAMASCOPE-RES-131K
    11. 30427
    Prev
    Next
    INDEX
    Explanations

    statements reflecting self-awareness and personal reflection

    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
    imple
    -0.06
     we
    -0.06
     tang
    -0.06
    aka
    -0.06
    imb
    -0.06
    imo
    -0.06
    aal
    -0.06
     my
    -0.05
    Slot
    -0.05
     meis
    -0.05
    POSITIVE LOGITS
    缼
    0.09
     supposedly
    0.08
    ENCHMARK
    0.08
     allegedly
    0.07
     supposed
    0.07
     Ñıк
    0.07
     rtrim
    0.07
     ÙĪØ£ÙĨ
    0.07
    ì¹Ń
    0.07
     nackte
    0.07
    Activations Density 0.042%

    No Known Activations