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

    Neuronpedia

    Jacobian LensNEW
    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. 119233
    Prev
    Next
    INDEX
    Explanations

    references to royal jewelry and historical royal events

    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
    district
    -0.07
     district
    -0.06
    strt
    -0.06
    ptal
    -0.06
     Celt
    -0.06
     sitio
    -0.06
    ambre
    -0.06
    District
    -0.06
    ť
    -0.06
    ×¢
    -0.06
    POSITIVE LOGITS
     Prince
    0.08
    iani
    0.07
     Princess
    0.07
     Dillon
    0.07
     princ
    0.06
    roy
    0.06
     roy
    0.06
     prince
    0.06
     royal
    0.06
    Prince
    0.06
    Activations Density 0.017%

    No Known Activations