© 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. 75057
    Prev
    Next
    INDEX
    Explanations

    questions and expressions of uncertainty or incredulity

    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
    lem
    -0.07
    quette
    -0.07
    uhl
    -0.06
     GOODMAN
    -0.06
    icket
    -0.06
    anship
    -0.06
    ãĥ¼ãĥ¬
    -0.06
     pon
    -0.06
    wen
    -0.06
    bat
    -0.06
    POSITIVE LOGITS
     possibly
    0.09
    à¹īà¸Ńย
    0.07
    possibly
    0.07
    illing
    0.06
    arda
    0.06
    enes
    0.06
    reu
    0.06
    _regions
    0.06
    ahu
    0.06
    룴
    0.06
    Activations Density 0.010%

    No Known Activations