© 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. 105686
    Prev
    Next
    INDEX
    Explanations

    pharmaceutical substances and their characteristics

    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
    arat
    -0.09
     สà¸ĸาà¸Ļ
    -0.07
    TestFixture
    -0.07
    ãģıãģł
    -0.07
    anke
    -0.07
    adena
    -0.07
     chân
    -0.07
    ansion
    -0.07
    è¬Ľ
    -0.07
    ÑĤÑİ
    -0.07
    POSITIVE LOGITS
     relief
    0.07
     Cherry
    0.07
     Fen
    0.06
     rounding
    0.06
     Beng
    0.06
     pain
    0.06
     syrup
    0.06
     van
    0.06
     ant
    0.06
     Brand
    0.06
    Activations Density 0.008%

    No Known Activations