Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 5646
    Prev
    Next
    INDEX
    Explanations

    words associated with cannabis

    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
    lette
    -0.06
     vintage
    -0.06
    iating
    -0.06
    tingham
    -0.06
    ugging
    -0.06
    eÅŁ
    -0.06
    mlink
    -0.06
    wards
    -0.06
    bourg
    -0.06
    à¥ĩण
    -0.06
    POSITIVE LOGITS
    ibal
    0.10
    abis
    0.10
     Cann
    0.09
     cann
    0.08
    ierge
    0.07
    nda
    0.07
    ood
    0.07
     Kann
    0.07
    abal
    0.07
    nn
    0.07
    Activations Density 0.001%

    No Known Activations