© 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. 4191
    Prev
    Next
    INDEX
    Explanations

    terms associated with medical treatment and health-related issues

    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
    âĢ¦↵
    -0.07
    ...↵
    -0.06
    arked
    -0.06
    ..↵
    -0.06
     slightly
    -0.06
    acs
    -0.06
    ↵
    -0.05
    /or
    -0.05
    vik
    -0.05
     âĢ¦↵
    -0.05
    POSITIVE LOGITS
    inclu
    0.09
    portun
    0.08
     Kaynak
    0.08
    .setViewport
    0.08
    //{{
    0.08
     голови
    0.07
    ÅĻez
    0.07
    BaÅŁ
    0.07
    άλι
    0.07
    CHandle
    0.07
    Activations Density 0.027%

    No Known Activations