© 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. 39757
    Prev
    Next
    INDEX
    Explanations

    instances of emotional expressions or sentiments in language

    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
    ording
    -0.07
    æ¸
    -0.07
    ¶
    -0.07
     ...)
    -0.06
    aso
    -0.06
    asu
    -0.06
    олÑĮно
    -0.06
    _Callback
    -0.06
    ÃŃs
    -0.06
    nam
    -0.06
    POSITIVE LOGITS
    anus
    0.07
    anos
    0.07
     пÑĢик
    0.07
    ytt
    0.07
    folio
    0.06
     There
    0.06
    erer
    0.06
     diá»ĩn
    0.06
    enk
    0.06
    tsky
    0.06
    Activations Density 0.008%

    No Known Activations