© 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. 3194
    Prev
    Next
    INDEX
    Explanations

    references to spiritual concepts and figures within religion

    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
    rint
    -0.06
    esin
    -0.06
    bard
    -0.06
    afari
    -0.06
    roupon
    -0.06
    ÙģÙĤ
    -0.06
    atten
    -0.06
    illet
    -0.06
     Common
    -0.06
    iversit
    -0.06
    POSITIVE LOGITS
     weap
    0.07
    еÑĪ
    0.07
    asure
    0.07
    Äįan
    0.07
     Gow
    0.07
     sway
    0.07
    åºĦ
    0.06
    컬
    0.06
     Nil
    0.06
     famously
    0.06
    Activations Density 0.027%

    No Known Activations