© 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. 22-LLAMASCOPE-RES-131K
    11. 3665
    Prev
    Next
    INDEX
    Explanations

    phrases related to research methodology and clinical trial design

    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
    forman
    -0.07
    Specification
    -0.07
    Å¡k
    -0.07
    âĢĮØ®
    -0.07
    arte
    -0.07
    .criteria
    -0.07
    ichten
    -0.06
    eday
    -0.06
    earn
    -0.06
    atern
    -0.06
    POSITIVE LOGITS
     participants
    0.09
     interventions
    0.09
     Participants
    0.08
     intervention
    0.08
     main
    0.08
     participant
    0.08
    MAIN
    0.07
     Intervention
    0.07
    Main
    0.07
     MAIN
    0.07
    Activations Density 0.003%

    No Known Activations