© 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. 15-LLAMASCOPE-RES-131K
    11. 87218
    Prev
    Next
    INDEX
    Explanations

    titles and roles associated with diplomatic positions

    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
    çļ
    -0.06
     migr
    -0.06
    umbing
    -0.06
    ording
    -0.06
    gart
    -0.06
     Outlet
    -0.06
     mobility
    -0.06
    ÑĢовод
    -0.06
    jez
    -0.06
    prenom
    -0.06
    POSITIVE LOGITS
    usk
    0.06
    ieg
    0.06
    inosaur
    0.06
    ushima
    0.06
    enan
    0.06
     çŃ
    0.06
     nhạc
    0.06
    iero
    0.06
    ingle
    0.06
     Äijô
    0.06
    Activations Density 0.003%

    No Known Activations