© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 77882
    Prev
    Next
    INDEX
    Explanations

    terms related to urgency and compliance issues

    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
    Č
    -0.07
     Check
    -0.06
     Howe
    -0.06
    unami
    -0.06
     Sweep
    -0.06
    angen
    -0.06
    anggan
    -0.06
    hang
    -0.06
     Golden
    -0.06
     Auto
    -0.05
    POSITIVE LOGITS
    imest
    0.07
    wat
    0.07
    ÏĦεÏģα
    0.07
    ToFront
    0.07
    utsch
    0.07
    -स
    0.07
    WND
    0.06
    eci
    0.06
    âĻ¡
    0.06
    ìĹ´
    0.06
    Activations Density 0.001%

    No Known Activations