© 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. 79036
    Prev
    Next
    INDEX
    Explanations

    terms related to pharmacology and pharmaceuticals

    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
    ائÙĦ
    -0.09
    idente
    -0.08
    uali
    -0.07
    adal
    -0.07
    iflower
    -0.07
    ichtig
    -0.07
    coles
    -0.06
    åİŁæĿ¥
    -0.06
    iyet
    -0.06
    iac
    -0.06
    POSITIVE LOGITS
     Morm
    0.07
    ALLY
    0.07
    other
    0.06
    ament
    0.06
    /or
    0.06
    /to
    0.06
    odb
    0.06
    embers
    0.06
    lick
    0.06
    older
    0.05
    Activations Density 0.003%

    No Known Activations