© 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 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. 59227
    Prev
    Next
    INDEX
    Explanations

    references to database operations and SQL terminology

    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
    etheus
    -0.07
    elfast
    -0.07
    Json
    -0.06
     functional
    -0.06
    ding
    -0.06
    arf
    -0.06
    eking
    -0.06
     dry
    -0.06
    ief
    -0.06
     XHTML
    -0.06
    POSITIVE LOGITS
     DriverManager
    0.07
    Abort
    0.07
     Abort
    0.06
    _OD
    0.06
     dialect
    0.06
    âĢĮâĢĮ
    0.06
    unsch
    0.06
     dÆ°
    0.06
    _UNIX
    0.06
    dde
    0.06
    Activations Density 0.004%

    No Known Activations