© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 29130
    Prev
    Next
    INDEX
    Explanations

    references to legal concepts and provisions regarding government actions and public dissent

    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
    åħ¹
    -0.07
    istributed
    -0.07
    ulsion
    -0.06
     roma
    -0.06
    ivre
    -0.06
    ẩm
    -0.06
    arella
    -0.06
    iams
    -0.06
    alley
    -0.06
    apture
    -0.06
    POSITIVE LOGITS
     ç±
    0.07
     Yük
    0.06
    191
    0.06
     Ñģвоб
    0.06
     Wireless
    0.06
     wireless
    0.06
     DeÄŁ
    0.06
    pth
    0.06
     Gandhi
    0.06
     Loaded
    0.06
    Activations Density 0.003%

    No Known Activations