© 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. 104789
    Prev
    Next
    INDEX
    Explanations

    references to Kim Jong-un and related 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
    aceous
    -0.08
    fak
    -0.07
    ISOString
    -0.07
    ahi
    -0.06
    986
    -0.06
    ORMAL
    -0.06
    ohana
    -0.06
    vester
    -0.06
    625
    -0.06
    ifice
    -0.06
    POSITIVE LOGITS
    usters
    0.07
    ÛĮدا
    0.07
    ãģķãģ¾
    0.07
     è¦
    0.06
     TD
    0.06
    alin
    0.06
    argar
    0.06
    алов
    0.06
     Jong
    0.06
    pla
    0.06
    Activations Density 0.004%

    No Known Activations