© 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. 41596
    Prev
    Next
    INDEX
    Explanations

    content related to costs and financial implications in regulatory contexts

    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
    DisplayStyle
    -0.07
    oron
    -0.07
    pered
    -0.06
    oux
    -0.06
    isen
    -0.06
    olean
    -0.06
     laut
    -0.06
    itorio
    -0.06
    agus
    -0.06
    icio
    -0.06
    POSITIVE LOGITS
     burden
    0.08
     burdens
    0.08
     costs
    0.07
    .datas
    0.07
     compliance
    0.07
     Compliance
    0.07
     Bur
    0.06
     implementation
    0.06
    .ejb
    0.06
    ê°Ħ
    0.06
    Activations Density 0.008%

    No Known Activations