© 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. 39007
    Prev
    Next
    INDEX
    Explanations

    specific dates and numerical values

    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
    0
    -0.09
    1
    -0.07
     morning
    -0.07
     Morning
    -0.07
    luet
    -0.07
     Spring
    -0.07
     jan
    -0.07
    æĺ¥
    -0.07
    01
    -0.07
     spring
    -0.06
    POSITIVE LOGITS
    umont
    0.07
     VÅ¡ech
    0.07
    æľ«
    0.07
    ãĥ³ãĥĩãĤ£
    0.07
     withObject
    0.07
    ONGLONG
    0.07
    ãĥ³ãĥĨ
    0.07
     Zwe
    0.07
    غات
    0.07
    etleri
    0.07
    Activations Density 0.069%

    No Known Activations