© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 125064
    Prev
    Next
    INDEX
    Explanations

    terms related to regulatory compliance and liability in international business

    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
     childhood
    -0.06
     emot
    -0.06
     Thr
    -0.06
    ÃŃ
    -0.06
     Municipal
    -0.06
     urban
    -0.06
    ţ
    -0.06
    δ
    -0.05
     portable
    -0.05
     å¼
    -0.05
    POSITIVE LOGITS
     Customs
    0.11
     customs
    0.10
     Duty
    0.09
     Border
    0.09
     taxp
    0.08
     importing
    0.08
     import
    0.08
     duty
    0.08
     foreign
    0.08
    Border
    0.08
    Activations Density 0.008%

    No Known Activations