© 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. 3601
    Prev
    Next
    INDEX
    Explanations

    associations between creativity and mental health within the context of various studies and applications

    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
     currently
    -0.06
     three
    -0.06
     Zub
    -0.06
     two
    -0.05
    æĺ¯æĪij
    -0.05
     five
    -0.05
    irit
    -0.05
     twice
    -0.05
    zl
    -0.05
     culmination
    -0.05
    POSITIVE LOGITS
     various
    0.15
    Various
    0.13
     Various
    0.13
     either
    0.13
    either
    0.12
    Either
    0.11
     EITHER
    0.11
    åIJĦç§į
    0.10
     Either
    0.10
     çeÅŁitli
    0.10
    Activations Density 0.069%

    No Known Activations