© 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. 55638
    Prev
    Next
    INDEX
    Explanations

    references to systemic abuse and accountability

    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
    vrier
    -0.09
     extradition
    -0.07
     Fate
    -0.07
    ãģłãģª
    -0.06
     tamb
    -0.06
    anzi
    -0.06
    ccione
    -0.06
    ictim
    -0.06
    endet
    -0.06
    اÙģع
    -0.06
    POSITIVE LOGITS
     reforms
    0.08
     fail
    0.08
     reform
    0.08
     culture
    0.07
     system
    0.07
     failures
    0.07
     report
    0.06
    æĺĩ
    0.06
     cultures
    0.06
     systematic
    0.06
    Activations Density 0.042%

    No Known Activations