© 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. 76862
    Prev
    Next
    INDEX
    Explanations

    instances of surprise or unexpected events

    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
    .scalablytyped
    -0.08
    DisplayStyle
    -0.07
    ajs
    -0.07
     thous
    -0.07
    ëł´
    -0.07
    ActivityIndicatorView
    -0.07
    /network
    -0.07
    (=)
    -0.06
     недели
    -0.06
    ÑĨик
    -0.06
    POSITIVE LOGITS
     surprise
    0.17
     unexpected
    0.17
    unexpected
    0.15
     Surprise
    0.15
     surprises
    0.15
     Unexpected
    0.14
    Unexpected
    0.14
     unexpectedly
    0.13
     surprised
    0.12
     surpr
    0.12
    Activations Density 0.051%

    No Known Activations