© 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. 16357
    Prev
    Next
    INDEX
    Explanations

    words related to neurotransmitters and their effects

    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
    ÏĨη
    -0.07
    ings
    -0.07
    arat
    -0.07
     Phelps
    -0.07
    invert
    -0.06
    alling
    -0.06
    .mj
    -0.06
    ak
    -0.06
    /desktop
    -0.06
    sto
    -0.06
    POSITIVE LOGITS
    -rich
    0.10
    ergic
    0.09
    -containing
    0.08
    emia
    0.07
    -star
    0.07
    richt
    0.07
     deficiency
    0.07
    strcasecmp
    0.07
    -based
    0.07
    aceous
    0.06
    Activations Density 0.064%

    No Known Activations