© 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. 81518
    Prev
    Next
    INDEX
    Explanations

    terms related to advanced mathematical concepts and structures

    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
    uve
    -0.06
     Sant
    -0.06
    705
    -0.06
    zo
    -0.06
    coni
    -0.06
    zar
    -0.06
    568
    -0.06
    ROW
    -0.06
     à¹Ĩ
    -0.06
     shaped
    -0.06
    POSITIVE LOGITS
     Vulkan
    0.07
    å¾ĭ
    0.07
     Dix
    0.07
    GENCY
    0.07
    óng
    0.06
     Lond
    0.06
    çİĩ
    0.06
    IVITY
    0.06
    bris
    0.06
    ÌĢ
    0.06
    Activations Density 0.186%

    No Known Activations