© 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. 31267
    Prev
    Next
    INDEX
    Explanations

    references to art collections and exhibitions

    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
    æ°ı
    -0.06
    MeasureSpec
    -0.06
    Ñij
    -0.06
    csrf
    -0.06
    exampleInputEmail
    -0.06
    лим
    -0.06
    .ASCII
    -0.06
    uai
    -0.06
    iert
    -0.06
    andid
    -0.06
    POSITIVE LOGITS
     collection
    0.09
    collection
    0.08
     collections
    0.08
     permanent
    0.08
    Collection
    0.08
     Collection
    0.07
     perman
    0.07
    Permanent
    0.07
    -transitional
    0.07
    -collection
    0.07
    Activations Density 0.006%

    No Known Activations