© 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. 15-LLAMASCOPE-RES-131K
    11. 104289
    Prev
    Next
    INDEX
    Explanations

    concepts related to opportunity and transformative experiences

    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
    reature
    -0.08
    elpers
    -0.08
    ::*
    -0.08
    inou
    -0.07
     Redistribution
    -0.07
    266
    -0.07
    else
    -0.07
    ëĿ¼ëıĦ
    -0.07
    imilar
    -0.07
    avenport
    -0.07
    POSITIVE LOGITS
     namely
    0.07
     totiž
    0.07
     nä
    0.07
    nam
    0.07
     yani
    0.07
    lü
    0.06
     Roy
    0.06
    .k
    0.06
     absolutely
    0.05
     and
    0.05
    Activations Density 0.048%

    No Known Activations