© 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. 80182
    Prev
    Next
    INDEX
    Explanations

    terms related to cannabis consumption methods and products

    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
     Paras
    -0.07
    lue
    -0.06
    лагод
    -0.06
    γκα
    -0.06
    ÑıÑĩ
    -0.06
    ollar
    -0.06
    oise
    -0.06
    åĪĢ
    -0.06
    odo
    -0.06
    бо
    -0.06
    POSITIVE LOGITS
    issy
    0.09
     aeros
    0.07
     vaping
    0.07
     Lung
    0.07
     seedu
    0.07
    -device
    0.07
    ameleon
    0.07
     inhal
    0.07
     atom
    0.07
     lungs
    0.07
    Activations Density 0.002%

    No Known Activations