© 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 EvalsExportsinterp-engineNEWAPI 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. 108057
    Prev
    Next
    INDEX
    Explanations

    references to water-related issues and infrastructure

    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
     Denn
    -0.07
    oa
    -0.07
    ongo
    -0.07
    uch
    -0.07
    pheric
    -0.06
    iki
    -0.06
     åĨĨ
    -0.06
    hta
    -0.06
    oen
    -0.06
     Dund
    -0.06
    POSITIVE LOGITS
    ë¡Ŀ
    0.08
     eskort
    0.07
    edBy
    0.07
    STITUTE
    0.07
    isÃŃ
    0.07
    Radians
    0.06
    amentals
    0.06
    mojom
    0.06
    ISBN
    0.06
    \\\\
    0.06
    Activations Density 0.340%

    No Known Activations