© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 40334
    Prev
    Next
    INDEX
    Explanations

    references to religious figures and their significance

    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
    ffa
    -0.08
    steen
    -0.08
    å·ŀ
    -0.07
    ibel
    -0.07
    aleb
    -0.07
    itm
    -0.07
     Ả
    -0.07
    inth
    -0.07
    ibrator
    -0.07
    raç
    -0.07
    POSITIVE LOGITS
     Vatican
    0.07
     retirement
    0.07
     worldwide
    0.07
     world
    0.07
     Beat
    0.07
     Pop
    0.06
     pap
    0.06
     Retirement
    0.06
    erview
    0.06
     Rome
    0.06
    Activations Density 0.003%

    No Known Activations