© 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 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. 106643
    Prev
    Next
    INDEX
    Explanations

    references to medical prescriptions and the healthcare system

    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
    Türkiye
    -0.08
    NEL
    -0.08
    ëŁ
    -0.08
    jong
    -0.07
    .***
    -0.07
    assa
    -0.07
    ãģ§ãģĻãģŃ
    -0.07
    jedn
    -0.07
    nels
    -0.07
     oby
    -0.07
    POSITIVE LOGITS
     Mr
    0.06
     he
    0.06
     Morales
    0.06
     she
    0.06
    outil
    0.06
     —
    0.06
     another
    0.06
     spokesman
    0.06
    ,
    0.06
     Herrera
    0.05
    Activations Density 1.382%

    No Known Activations