© 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. 119281
    Prev
    Next
    INDEX
    Explanations

    geographic locations or state abbreviations

    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
    esco
    -0.08
    ESCO
    -0.06
     meaning
    -0.06
    agos
    -0.05
    asar
    -0.05
     Fl
    -0.05
    .tex
    -0.05
     keycode
    -0.05
    را
    -0.05
     Sky
    -0.05
    POSITIVE LOGITS
     ãģ¾
    0.08
    endance
    0.07
    arget
    0.07
    åŃĿ
    0.07
     Zimmerman
    0.07
    'gc
    0.07
    ีà¸Ńย
    0.06
    anmar
    0.06
    inesis
    0.06
    acman
    0.06
    Activations Density 0.007%

    No Known Activations