© 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. 15-LLAMASCOPE-RES-131K
    11. 27084
    Prev
    Next
    INDEX
    Explanations

    references to baptism and religious experiences

    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
    .nlm
    -0.07
    Ñĩив
    -0.07
     обоÑĢ
    -0.07
    าà¸į
    -0.07
    aggi
    -0.07
     sacr
    -0.07
     Dud
    -0.06
    ITTE
    -0.06
    DEX
    -0.06
    å¼
    -0.06
    POSITIVE LOGITS
     agua
    0.07
     water
    0.07
     gee
    0.06
     водой
    0.06
    oman
    0.06
     symbol
    0.06
    271
    0.06
    omatic
    0.06
    çļ
    0.06
     Brock
    0.06
    Activations Density 0.009%

    No Known Activations