© 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. 128777
    Prev
    Next
    INDEX
    Explanations

    numerical data and related units of measurement

    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
    дейÑģÑĤв
    -0.07
    ÙĪاÙĨ
    -0.07
    ito
    -0.06
    isphere
    -0.06
    à¥ģव
    -0.06
    wiki
    -0.06
    oser
    -0.06
    %f
    -0.06
     Age
    -0.06
     jl
    -0.06
    POSITIVE LOGITS
    akov
    0.07
    achten
    0.07
    uren
    0.07
    ibling
    0.07
    rella
    0.06
    Äħż
    0.06
    oje
    0.06
    oods
    0.06
    anagan
    0.06
    ","#
    0.06
    Activations Density 0.000%

    No Known Activations