© 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. 55457
    Prev
    Next
    INDEX
    Explanations

    terms related to the production, sale, and regulation of 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
     Stam
    -0.06
    urat
    -0.06
    TL
    -0.06
     ÑĦÑĥнда
    -0.06
     downt
    -0.06
     Projects
    -0.06
    ickey
    -0.06
     ber
    -0.06
    ependency
    -0.06
    иплом
    -0.06
    POSITIVE LOGITS
     retail
    0.10
     distribution
    0.10
     market
    0.10
     sale
    0.10
    -market
    0.09
     sales
    0.09
    éĶĢåĶ®
    0.09
     Distribution
    0.09
     sell
    0.09
     selling
    0.09
    Activations Density 0.050%

    No Known Activations