© 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. 40776
    Prev
    Next
    INDEX
    Explanations

    references to motherhood and related theological concepts

    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
    inden
    -0.07
    apiro
    -0.07
    仲
    -0.07
     Tao
    -0.07
    aska
    -0.06
    ÏĥÏĦά
    -0.06
     Sci
    -0.05
     Episcopal
    -0.05
     SAP
    -0.05
     Sage
    -0.05
    POSITIVE LOGITS
     Calvin
    0.08
     lục
    0.07
     Belg
    0.07
     Singap
    0.07
    ÏĪη
    0.07
     âĪ¨
    0.07
     meg
    0.06
     Billy
    0.06
    itage
    0.06
    ipel
    0.06
    Activations Density 0.026%

    No Known Activations