© 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. 85266
    Prev
    Next
    INDEX
    Explanations

    terms related to cannabis cultivation and yield

    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
    NAV
    -0.07
    Ïħν
    -0.06
    buat
    -0.06
    nga
    -0.06
    éķ
    -0.06
     اÙĦطب
    -0.06
     tablesp
    -0.06
    leon
    -0.06
    atti
    -0.06
     aktuellen
    -0.06
    POSITIVE LOGITS
    ä¾
    0.08
     grow
    0.08
     growth
    0.07
    /***/
    0.07
    anoi
    0.07
    afort
    0.07
    eterminate
    0.07
    icot
    0.07
    Grow
    0.06
     growers
    0.06
    Activations Density 0.004%

    No Known Activations