© 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. 125734
    Prev
    Next
    INDEX
    Explanations

    actions related to construction, renovation, and maintenance

    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
    gom
    -0.07
    /not
    -0.07
    ascar
    -0.06
     Tuy
    -0.06
     Keller
    -0.06
     Ù¾ÛĮر
    -0.06
    pas
    -0.06
    /be
    -0.06
    /about
    -0.06
    боÑĢа
    -0.06
    POSITIVE LOGITS
     and
    0.08
    ibold
    0.07
     entire
    0.07
    undi
    0.07
    ansion
    0.07
    .Xaml
    0.06
    'gc
    0.06
    uluk
    0.06
    ierung
    0.06
     xong
    0.06
    Activations Density 0.022%

    No Known Activations