© 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. 129306
    Prev
    Next
    INDEX
    Explanations

    references to dopamine and its 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
     SetProperty
    -0.08
    usi
    -0.07
    isay
    -0.07
    orum
    -0.07
    syntax
    -0.07
    .ribbon
    -0.07
    tight
    -0.07
    lý
    -0.07
    quam
    -0.06
    ifr
    -0.06
    POSITIVE LOGITS
    pler
    0.08
    agne
    0.07
    sters
    0.07
     Hed
    0.06
    571
    0.06
    py
    0.06
    ught
    0.06
    ument
    0.06
    iazza
    0.06
    amine
    0.06
    Activations Density 0.012%

    No Known Activations