© 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. 92421
    Prev
    Next
    INDEX
    Explanations

    references to payment processes and order fulfillment

    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
     straight
    -0.07
    ë¡Ģ
    -0.07
    缴
    -0.06
     è±
    -0.06
    ual
    -0.06
    inton
    -0.06
    erties
    -0.06
    ington
    -0.06
     Surface
    -0.06
    frau
    -0.06
    POSITIVE LOGITS
     orders
    0.07
     order
    0.07
    Desk
    0.07
    endi
    0.06
     funds
    0.06
    orders
    0.06
    order
    0.06
    805
    0.06
    -order
    0.06
     Orders
    0.06
    Activations Density 0.006%

    No Known Activations