© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 2897
    Prev
    Next
    INDEX
    Explanations

    references to Luxembourg and its economic characteristics

    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
     Vancouver
    -0.09
     Seattle
    -0.08
    Seattle
    -0.08
    ancouver
    -0.07
    eniz
    -0.07
    qrst
    -0.07
    monton
    -0.07
    abcdefghijkl
    -0.07
    ANDLE
    -0.07
     Edmonton
    -0.07
    POSITIVE LOGITS
     Luxembourg
    0.13
    .lu
    0.09
    embourg
    0.08
    Lux
    0.08
     sens
    0.07
    ancy
    0.06
     lux
    0.06
    ãĥ«ãĤ¯
    0.06
     Slim
    0.06
    ange
    0.06
    Activations Density 0.029%

    No Known Activations