© 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. 4519
    Prev
    Next
    INDEX
    Explanations

    references to the membership and governmental structures of states and nations

    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
    omba
    -0.07
    gee
    -0.06
    TriState
    -0.06
    اج
    -0.06
    chop
    -0.06
     Fields
    -0.06
    ultz
    -0.06
    iasi
    -0.06
    ł
    -0.06
    ä¸Ģ个人
    -0.06
    POSITIVE LOGITS
    errat
    0.07
    kits
    0.07
    们
    0.07
    éĻħ
    0.06
    alsex
    0.06
    alse
    0.06
    fur
    0.06
     pairs
    0.06
     Pavilion
    0.06
    ags
    0.06
    Activations Density 0.023%

    No Known Activations