© 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. 86452
    Prev
    Next
    INDEX
    Explanations

    terms related to payment deadlines and invoicing

    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
    bour
    -0.06
    cha
    -0.06
    382
    -0.06
     Luo
    -0.06
     Beam
    -0.06
     Cust
    -0.06
     cust
    -0.06
    907
    -0.06
     couldn
    -0.06
    ÙĬات
    -0.06
    POSITIVE LOGITS
    寸
    0.08
    yte
    0.07
     invo
    0.07
    ocl
    0.07
     Nichols
    0.07
     MASTER
    0.07
    оÑĢÑĤ
    0.07
     Unless
    0.07
    Unless
    0.07
     Surv
    0.06
    Activations Density 0.006%

    No Known Activations