© 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. 125593
    Prev
    Next
    INDEX
    Explanations

    references to quantities or collections, particularly in the context of social and cultural topics

    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
    792
    -0.07
     uncert
    -0.07
     jež
    -0.07
    âĢĮشدÙĩ
    -0.07
    lander
    -0.07
    stoup
    -0.07
    .LayoutStyle
    -0.06
    END
    -0.06
    -ci
    -0.06
     gauche
    -0.06
    POSITIVE LOGITS
    ãĤ
    0.07
    yne
    0.07
    iola
    0.07
    aney
    0.07
    hong
    0.07
    iyim
    0.07
    place
    0.06
    emp
    0.06
    abic
    0.06
    ivé
    0.06
    Activations Density 0.008%

    No Known Activations