© 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. 127249
    Prev
    Next
    INDEX
    Explanations

    terms related to cannabinoids 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
    aniem
    -0.07
    طع
    -0.07
    enville
    -0.07
    egin
    -0.07
    iffe
    -0.07
     Metals
    -0.07
    igin
    -0.06
    irm
    -0.06
    ograd
    -0.06
    anding
    -0.06
    POSITIVE LOGITS
    onga
    0.07
     recreational
    0.07
     extracted
    0.07
     addictive
    0.07
     THC
    0.07
     recre
    0.07
    麻
    0.06
     Schedule
    0.06
     tet
    0.06
     psycho
    0.06
    Activations Density 0.018%

    No Known Activations