© 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. 71263
    Prev
    Next
    INDEX
    Explanations

    phrases related to health and safety measures

    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
    laughter
    -0.07
     atd
    -0.06
    ErrorException
    -0.06
    ymes
    -0.06
    GLOBALS
    -0.06
    cÃŃ
    -0.06
    anz
    -0.06
    å¿į
    -0.06
    ushima
    -0.06
     δε
    -0.06
    POSITIVE LOGITS
    chalk
    0.09
     Offensive
    0.07
    phan
    0.07
     productivity
    0.07
    uchs
    0.07
     offense
    0.07
    productive
    0.07
    аÑĢÑĸ
    0.07
    DED
    0.06
    รว
    0.06
    Activations Density 0.062%

    No Known Activations