© 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. 127373
    Prev
    Next
    INDEX
    Explanations

    expressions of satisfaction or disappointment regarding experiences, particularly in entertainment contexts

    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
    تÙħ
    -0.06
    tip
    -0.06
    aura
    -0.06
    aro
    -0.06
    ogie
    -0.05
    _acquire
    -0.05
    .dp
    -0.05
    ãĥĸãĥ«
    -0.05
    ought
    -0.05
     Rice
    -0.05
    POSITIVE LOGITS
     disappoint
    0.17
     disappointment
    0.15
     disappointing
    0.14
     disappointed
    0.13
     expectations
    0.11
     surprise
    0.10
     surprises
    0.10
     unexpected
    0.09
     expectation
    0.09
    unexpected
    0.08
    Activations Density 0.112%

    No Known Activations