© 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. 76477
    Prev
    Next
    INDEX
    Explanations

    content related to health risks and safety concerns for vulnerable populations

    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
    ãĤ¤ãĤ¯
    -0.07
    anse
    -0.07
     ÑģоÑĢ
    -0.06
    æ²ĸ
    -0.06
     Relief
    -0.06
     intptr
    -0.06
     cakes
    -0.06
    amation
    -0.06
    bsd
    -0.06
    Ïħν
    -0.06
    POSITIVE LOGITS
     coron
    0.08
     safety
    0.08
     Saf
    0.07
     Fatal
    0.07
    afe
    0.07
     deadly
    0.07
     Sleep
    0.07
     fatal
    0.07
     breathing
    0.07
     breath
    0.07
    Activations Density 0.001%

    No Known Activations