© 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. 79062
    Prev
    Next
    INDEX
    Explanations

    terms related to healthcare, specifically electronic government services and mobile health technologies

    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
     Bien
    -0.08
     Kraj
    -0.08
    ateg
    -0.08
    ÑĦек
    -0.07
    kal
    -0.07
    atrix
    -0.07
    YYY
    -0.06
    ilden
    -0.06
    eel
    -0.06
    locs
    -0.06
    POSITIVE LOGITS
     technology
    0.08
     concept
    0.08
     technologies
    0.07
     applications
    0.07
    -enabled
    0.07
    .IContainer
    0.07
    -ready
    0.07
     project
    0.07
    -related
    0.06
     promised
    0.06
    Activations Density 0.042%

    No Known Activations