© 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. 73103
    Prev
    Next
    INDEX
    Explanations

    references to political negotiations and agreements involving North Korea

    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
    à¸Ł
    -0.08
    ाध
    -0.08
    inyin
    -0.07
    ampie
    -0.07
     heter
    -0.07
    ãĤ¿ãĥ«
    -0.07
    NavController
    -0.07
    ancellable
    -0.07
    ево
    -0.07
    olib
    -0.06
    POSITIVE LOGITS
     Kim
    0.09
    Kim
    0.08
    ovich
    0.07
    addtogroup
    0.07
     Pyongyang
    0.06
    ÙĪÙĨÙĩ
    0.06
     NK
    0.06
     Korean
    0.06
    kim
    0.06
     æľĿ
    0.06
    Activations Density 0.023%

    No Known Activations