© 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. 9-LLAMASCOPE-RES-131K
    11. 96670
    Prev
    Next
    INDEX
    Explanations

    connections between mental health, particularly bipolar disorder, and creativity

    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
    apan
    -0.08
    razier
    -0.07
    avis
    -0.07
    itre
    -0.07
    ests
    -0.07
    gorm
    -0.07
    apel
    -0.07
    foon
    -0.07
    enties
    -0.07
    lok
    -0.07
    POSITIVE LOGITS
     [
    0.06
    547
    0.06
     mell
    0.06
    iye
    0.06
    ÑĢод
    0.06
    0.05
    735
    0.05
    æ³
    0.05
    *
    0.05
     unrelated
    0.05
    Activations Density 0.137%

    No Known Activations