© 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. 60952
    Prev
    Next
    INDEX
    Explanations

    questions and inquiries that express curiosity or uncertainty

    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
    976
    -0.07
    ãĥ³ãĥĸ
    -0.07
    edly
    -0.07
    897
    -0.06
    cher
    -0.06
    Æ¡
    -0.06
    ozy
    -0.06
    rish
    -0.06
    inet
    -0.06
    imer
    -0.06
    POSITIVE LOGITS
     perhaps
    0.08
     maybe
    0.08
     might
    0.08
     wonder
    0.08
     could
    0.08
    adera
    0.07
     possibly
    0.07
     Could
    0.07
     wouldn
    0.07
    èĥ½
    0.07
    Activations Density 0.037%

    No Known Activations