© 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. 123666
    Prev
    Next
    INDEX
    Explanations

    phrases indicating 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
    dio
    -0.07
    нÑıв
    -0.06
     disag
    -0.06
    umbing
    -0.06
    /uploads
    -0.06
    ÑĦоÑĢма
    -0.05
    vise
    -0.05
    .samples
    -0.05
     close
    -0.05
    ils
    -0.05
    POSITIVE LOGITS
     surprise
    0.15
     Surprise
    0.14
     surprises
    0.13
     discovery
    0.11
     surprised
    0.10
     surpr
    0.09
     mystery
    0.09
     pÅĻekvap
    0.09
     Discovery
    0.09
    reveal
    0.08
    Activations Density 0.036%

    No Known Activations