© 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. 60925
    Prev
    Next
    INDEX
    Explanations

    references to specific insects, particularly butterflies

    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
     acomp
    -0.06
     pitch
    -0.06
     segreg
    -0.06
    омен
    -0.06
     horse
    -0.05
    mith
    -0.05
    orro
    -0.05
     frog
    -0.05
    309
    -0.05
     sab
    -0.05
    POSITIVE LOGITS
    ÙĤات
    0.07
    doi
    0.07
    ispers
    0.07
     Returned
    0.07
     retour
    0.07
    .return
    0.07
    ectors
    0.06
    HOME
    0.06
    ĶåĽŀ
    0.06
     return
    0.06
    Activations Density 0.000%

    No Known Activations