© 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. 4217
    Prev
    Next
    INDEX
    Explanations

    phrases related to event attendance and participation

    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
    amas
    -0.08
    ä¼łå¥ĩ
    -0.07
    بت
    -0.06
    agn
    -0.06
    imi
    -0.06
    ÌĢ
    -0.06
    ámara
    -0.06
    .jasper
    -0.06
    473
    -0.06
    ior
    -0.06
    POSITIVE LOGITS
     event
    0.10
     меÑĢопÑĢи
    0.08
    äºĭ件
    0.07
    orget
    0.06
    ÎŃλ
    0.06
     proceedings
    0.06
     affair
    0.06
    .event
    0.06
    	event
    0.06
     venue
    0.06
    Activations Density 0.023%

    No Known Activations