© 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. 87792
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to countries and regions

    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
     Ranch
    -0.07
    sss
    -0.07
    iton
    -0.07
    linger
    -0.07
    elin
    -0.06
    eson
    -0.06
    lessly
    -0.06
    eton
    -0.06
    ibi
    -0.06
    èĨľ
    -0.06
    POSITIVE LOGITS
    -Russian
    0.09
    -American
    0.09
    ian
    0.09
    shire
    0.07
    uese
    0.07
    ese
    0.07
    outh
    0.07
    ors
    0.07
    ķ
    0.07
    ç±į
    0.06
    Activations Density 0.023%

    No Known Activations