© 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 EvalsExportsinterp-engineNEWAPI 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. 27424
    Prev
    Next
    INDEX
    Explanations

    statements involving historical legends and notable figures

    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
    roupon
    -0.06
    arakter
    -0.06
    wang
    -0.06
    usive
    -0.06
     meisten
    -0.06
    ller
    -0.06
     newest
    -0.06
    åŃ£
    -0.06
    inerary
    -0.06
    äs
    -0.06
    POSITIVE LOGITS
     somewhere
    0.08
     Ñıк
    0.07
     ghost
    0.06
    igm
    0.06
    lick
    0.06
    loom
    0.06
    :date
    0.06
     allegedly
    0.06
     orig
    0.06
    ä¸Ģ度
    0.06
    Activations Density 0.031%

    No Known Activations