© 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 EvalsExportsAPI 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. 59331
    Prev
    Next
    INDEX
    Explanations

    country names

    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
    ourt
    -0.07
    važ
    -0.07
    rine
    -0.07
    istrat
    -0.07
    eka
    -0.06
    .tk
    -0.06
     superhero
    -0.06
    velope
    -0.06
    dain
    -0.06
    .intValue
    -0.06
    POSITIVE LOGITS
    /gpl
    0.06
     gim
    0.06
    ERRU
    0.06
    ̣
    0.06
    cctor
    0.06
     nuest
    0.06
     italic
    0.06
    ÄŁitim
    0.06
    lernen
    0.06
    antis
    0.06
    Activations Density 0.018%

    No Known Activations