© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 5947
    Prev
    Next
    INDEX
    Explanations

    references to digital platforms and processes related to commerce and purchasing

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    /renderer
    -0.07
    oucher
    -0.06
    θεÏģ
    -0.06
     swallowing
    -0.06
     Telecom
    -0.06
     subur
    -0.06
     dim
    -0.06
    unsch
    -0.06
     arts
    -0.06
     anal
    -0.06
    POSITIVE LOGITS
     transaction
    0.08
    æĴ®
    0.07
     vet
    0.07
    eyJ
    0.07
     Accepted
    0.07
     transactions
    0.07
    ussels
    0.07
     exchange
    0.07
    ίδ
    0.07
    ìĹŃ
    0.07
    Activations Density 0.007%

    No Known Activations