© 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. 123867
    Prev
    Next
    INDEX
    Explanations

    aspects related to alcohol content and availability in beverages

    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
    pository
    -0.07
    atik
    -0.06
    åľŁ
    -0.06
    Įĵ
    -0.06
    нка
    -0.06
    EIF
    -0.06
     Newspaper
    -0.06
    errupted
    -0.06
    _utf
    -0.06
     Obr
    -0.06
    POSITIVE LOGITS
     alcohol
    0.08
    cohol
    0.08
     Alcohol
    0.07
    odka
    0.07
     grape
    0.07
    utra
    0.06
    spar
    0.06
    Contain
    0.06
     fort
    0.06
     алког
    0.06
    Activations Density 0.015%

    No Known Activations