© 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. 62832
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to SQL procedures and commands

    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
    à¥Ĥà¤Ł
    -0.07
    anel
    -0.07
    .plist
    -0.06
    DBus
    -0.06
    inÄĽ
    -0.06
     tarn
    -0.06
    ebra
    -0.06
     Inhal
    -0.06
    Abstract
    -0.06
    ccione
    -0.06
    POSITIVE LOGITS
     Maryland
    0.09
     Baltimore
    0.08
    ssql
    0.08
    SqlServer
    0.07
     Microsoft
    0.07
    ].[
    0.07
    Azure
    0.07
     dbo
    0.07
    dbo
    0.07
     Azure
    0.07
    Activations Density 0.015%

    No Known Activations