© 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. 83410
    Prev
    Next
    INDEX
    Explanations

    terms related to pharmaceutical drugs or medications

    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
    (æĹ¥
    -0.08
    adla
    -0.08
    /*č↵
    -0.08
    ocio
    -0.07
    .emf
    -0.07
    FRING
    -0.07
    /testing
    -0.07
    oog
    -0.07
    adiens
    -0.07
    &_
    -0.07
    POSITIVE LOGITS
    elor
    0.06
    âĢIJ
    0.06
    114
    0.06
     Feder
    0.06
    â
    0.05
    quit
    0.05
    Prem
    0.05
    âĢij
    0.05
     Klein
    0.05
     LGBTQ
    0.05
    Activations Density 0.001%

    No Known Activations