© 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. 17-LLAMASCOPE-RES-131K
    11. 127965
    Prev
    Next
    INDEX
    Explanations

    phrases related to creativity and motivation

    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
    ilde
    -0.07
    geh
    -0.07
    ÏĦαν
    -0.07
    estar
    -0.06
    ern
    -0.06
    essa
    -0.06
    олоÑĤ
    -0.06
    arest
    -0.06
    zw
    -0.06
    ocene
    -0.06
    POSITIVE LOGITS
    strup
    0.08
    zia
    0.07
    lesi
    0.07
     moments
    0.07
    fruit
    0.07
    лий
    0.07
    ãģ®ãĤĤ
    0.07
    ql
    0.07
    æĿIJ
    0.06
     voksen
    0.06
    Activations Density 0.015%

    No Known Activations