© 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. 28707
    Prev
    Next
    INDEX
    Explanations

    references to health, safety, and well-being, particularly related to individuals' rights and community concerns

    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
     Charity
    -0.07
    uko
    -0.07
    .simps
    -0.06
    بÛĮر
    -0.06
    \Mapping
    -0.06
    ÅĻet
    -0.06
     plat
    -0.06
    ç«
    -0.06
    åĬŁ
    -0.06
    @stop
    -0.06
    POSITIVE LOGITS
     welfare
    0.10
     health
    0.09
     needs
    0.09
     wellbeing
    0.08
    chwitz
    0.08
     interests
    0.07
     rights
    0.07
    health
    0.07
     Welfare
    0.07
    åģ¥åº·
    0.07
    Activations Density 0.028%

    No Known Activations