© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 125120
    Prev
    Next
    INDEX
    Explanations

    actions related to mixing or combining ingredients in cooking

    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
    kses
    -0.09
    ulen
    -0.08
    AZY
    -0.08
    ãģ°
    -0.08
    éné
    -0.08
    竹
    -0.08
    ascade
    -0.07
    VOKE
    -0.07
    agara
    -0.07
    бав
    -0.07
    POSITIVE LOGITS
     during
    0.07
     occasionally
    0.06
    ,
    0.06
     continuously
    0.06
     sóc
    0.06
     constantly
    0.06
     contin
    0.06
     only
    0.06
    ↵
    0.06
    contin
    0.05
    Activations Density 0.003%

    No Known Activations