© 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. 30560
    Prev
    Next
    INDEX
    Explanations

    references to the pandas DataFrame and its associated methods in programming code

    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
    gran
    -0.07
    Ùij
    -0.07
     Synd
    -0.07
     Carpenter
    -0.06
    RING
    -0.06
    lar
    -0.06
    ardo
    -0.06
     ust
    -0.06
     synd
    -0.06
    #undef
    -0.06
    POSITIVE LOGITS
    ify
    0.07
    509
    0.06
    /Foundation
    0.06
     Stealth
    0.06
    ertino
    0.06
    napshot
    0.06
    iej
    0.06
    aus
    0.06
    IFY
    0.06
    ColumnInfo
    0.06
    Activations Density 0.001%

    No Known Activations