© 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. 39931
    Prev
    Next
    INDEX
    Explanations

    references to artists and the artistic process

    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
    ovice
    -0.06
    wor
    -0.06
    paint
    -0.06
     paint
    -0.06
     paints
    -0.06
     lag
    -0.06
     irre
    -0.06
     adm
    -0.06
     painting
    -0.06
     Property
    -0.06
    POSITIVE LOGITS
     presses
    0.09
    paged
    0.08
    isy
    0.08
    å¾Ħ
    0.08
     Binding
    0.07
     bindings
    0.07
    à¸Īำหà¸Ļ
    0.07
    folios
    0.07
     Corm
    0.07
    ãĥ¼ãĥIJ
    0.07
    Activations Density 0.014%

    No Known Activations