© 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. 15-LLAMASCOPE-RES-131K
    11. 62324
    Prev
    Next
    INDEX
    Explanations

    terms related to health care and medical fields

    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
    swing
    -0.07
    ijo
    -0.06
     syndrome
    -0.06
    ØŃÙĤ
    -0.06
     CONDITIONS
    -0.06
    rames
    -0.06
    ificates
    -0.06
    ãĥ³ãĥĸ
    -0.06
    antage
    -0.06
    pher
    -0.06
    POSITIVE LOGITS
    orem
    0.09
    ureau
    0.07
    alus
    0.07
     jenter
    0.07
    enor
    0.07
    DMI
    0.06
    ováno
    0.06
     ç½
    0.06
    rita
    0.06
    ildo
    0.06
    Activations Density 0.180%

    No Known Activations