© 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. 62529
    Prev
    Next
    INDEX
    Explanations

    references to specific countries, primarily China and India

    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
    elsea
    -0.08
    nett
    -0.08
    elman
    -0.07
    ither
    -0.07
    å¼¥
    -0.07
    ControlEvents
    -0.07
    ingleton
    -0.06
    ennifer
    -0.06
     nÆ°á»Ľc
    -0.06
    utom
    -0.06
    POSITIVE LOGITS
    istrovstvÃŃ
    0.06
     apl
    0.06
    ãģ£ãģı
    0.06
    -utils
    0.06
    _MIDDLE
    0.06
    -addons
    0.06
    .chapter
    0.05
    ount
    0.05
     high
    0.05
     Bone
    0.05
    Activations Density 0.002%

    No Known Activations