© 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. 1292
    Prev
    Next
    INDEX
    Explanations

    quantities related to financial contracts and agreements

    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
    ÅĻet
    -0.07
    ekl
    -0.07
    èĦ
    -0.07
    داÙħ
    -0.06
    kte
    -0.06
     Dispatcher
    -0.06
    reature
    -0.06
    ardown
    -0.06
    lassen
    -0.06
    üz
    -0.06
    POSITIVE LOGITS
     paid
    0.08
     consultant
    0.07
     project
    0.07
     consultants
    0.07
     firms
    0.07
     hired
    0.07
     firm
    0.06
    oproject
    0.06
     expense
    0.06
     study
    0.06
    Activations Density 0.014%

    No Known Activations