© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 1264
    Prev
    Next
    INDEX
    Explanations

    information about liquor licensing and related regulations

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
     fib
    -0.07
    à¸Ľà¸£à¸°à¸ģ
    -0.06
    äm
    -0.06
     Breakfast
    -0.06
    endencies
    -0.06
     cook
    -0.06
     Appropri
    -0.05
     bil
    -0.05
    รà¸ĩ
    -0.05
    ĴĮ
    -0.05
    POSITIVE LOGITS
     alcohol
    0.13
     Alcohol
    0.12
    éħĴ
    0.12
    cohol
    0.10
     alcoholic
    0.10
     booze
    0.09
     алког
    0.09
     license
    0.08
     liquor
    0.08
     wine
    0.08
    Activations Density 0.033%

    No Known Activations