© 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. 39848
    Prev
    Next
    INDEX
    Explanations

    phrases related to the roles and interactions of healthcare professionals and patients

    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
    алеж
    -0.08
    ERGE
    -0.08
    rung
    -0.07
    >tag
    -0.07
     Stateless
    -0.07
    riz
    -0.07
    occo
    -0.07
    íĥĿ
    -0.07
     Äija
    -0.07
    رÙĪز
    -0.07
    POSITIVE LOGITS
     alike
    0.20
     respectively
    0.14
     mutual
    0.13
     mutually
    0.12
     respective
    0.11
     together
    0.10
     Mutual
    0.09
    mut
    0.09
     nhau
    0.09
    äºĴ
    0.08
    Activations Density 0.045%

    No Known Activations