© 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. 57442
    Prev
    Next
    INDEX
    Explanations

    terms related to cannabis and its components, particularly cannabinoids

    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
    oq
    -0.09
     addCriterion
    -0.08
    ope
    -0.07
    uluk
    -0.07
    ArgumentException
    -0.07
    ãĥ³ãĥij
    -0.07
    ovit
    -0.07
    vit
    -0.07
    erb
    -0.07
    oz
    -0.07
    POSITIVE LOGITS
    haft
    0.07
     extracted
    0.06
    ly
    0.06
     اÙħ
    0.05
     onFocus
    0.05
    æłª
    0.05
     nons
    0.05
     hydr
    0.05
    ̣
    0.05
     Feed
    0.05
    Activations Density 0.002%

    No Known Activations