© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 57865
    Prev
    Next
    INDEX
    Explanations

    expressions of surprise and evaluation of experiences

    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
     unfortunately
    -0.07
     Horton
    -0.07
     Brill
    -0.07
     understandably
    -0.06
    Unfortunately
    -0.06
     Unfortunately
    -0.06
    odo
    -0.06
    mast
    -0.06
    ãģ¾ãģł
    -0.06
    redo
    -0.06
    POSITIVE LOGITS
     surprise
    0.15
     surprising
    0.13
     surprises
    0.13
     surprisingly
    0.13
     Surprise
    0.13
    unexpected
    0.12
     unexpected
    0.12
     surpr
    0.11
     unexpectedly
    0.11
     surprised
    0.11
    Activations Density 0.032%

    No Known Activations