© 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. 87650
    Prev
    Next
    INDEX
    Explanations

    words associated with successful business operations and services

    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
    oksen
    -0.06
    ixa
    -0.06
     subsequent
    -0.06
    нÑĸй
    -0.06
    okus
    -0.06
     Consort
    -0.06
     dateFormatter
    -0.06
     challeng
    -0.06
    æľĽ
    -0.06
     identified
    -0.06
    POSITIVE LOGITS
    thers
    0.07
    heim
    0.07
    rim
    0.06
     lorem
    0.06
    alez
    0.06
    ambre
    0.06
    __[
    0.06
     vat
    0.06
    nesc
    0.06
    aro
    0.06
    Activations Density 0.000%

    No Known Activations