© 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. 80394
    Prev
    Next
    INDEX
    Explanations

    phrases expressing excitement or anticipation about events and gatherings

    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
    èĪĪ
    -0.06
    ieber
    -0.06
    aware
    -0.06
    969
    -0.06
    imuth
    -0.06
    ingle
    -0.06
    ãģĻãģİ
    -0.06
    aux
    -0.06
    chem
    -0.06
    ux
    -0.06
    POSITIVE LOGITS
     opportunity
    0.09
     chance
    0.08
     Opportunity
    0.08
     opportunities
    0.08
     Chance
    0.07
     gratis
    0.07
    Chance
    0.07
    linger
    0.07
    æľºä¼ļ
    0.07
     decent
    0.07
    Activations Density 0.042%

    No Known Activations