© 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. 29260
    Prev
    Next
    INDEX
    Explanations

    titles or names associated with royalty or formal titles

    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
    errer
    -0.08
    ascar
    -0.07
    áky
    -0.07
    èn
    -0.07
    chy
    -0.07
    ohana
    -0.06
     GANG
    -0.06
    .Pod
    -0.06
    uent
    -0.06
    üven
    -0.06
    POSITIVE LOGITS
     tradition
    0.08
    olas
    0.07
     wearer
    0.06
    trad
    0.06
     civic
    0.06
     Dut
    0.06
     traditionally
    0.06
     traditional
    0.06
    اÙĦØ´
    0.06
     page
    0.06
    Activations Density 0.006%

    No Known Activations