© 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 EvalsExportsinterp-engineNEWAPI 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. 86608
    Prev
    Next
    INDEX
    Explanations

    biochemical terms related to dopamine and its metabolites in relation to autism and other neurological conditions

    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
    ocommerce
    -0.08
    kenin
    -0.07
    umont
    -0.07
    apikey
    -0.07
    NY
    -0.07
    tml
    -0.07
    lund
    -0.07
    ejs
    -0.07
    kud
    -0.06
    dependencies
    -0.06
    POSITIVE LOGITS
    quot
    0.07
     Invent
    0.07
     normalized
    0.07
     total
    0.07
     quot
    0.07
     markers
    0.06
    markers
    0.06
    marker
    0.06
     levels
    0.06
     invent
    0.06
    Activations Density 0.054%

    No Known Activations