© 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. 108109
    Prev
    Next
    INDEX
    Explanations

    elements related to cultural expressions and cuisine

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Foreign language words embedded in predominantly English text, representing various languages including Spanish, Slavic languages, Latin, French, Japanese, Korean, and others.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    ofile
    -0.08
     peÄį
    -0.08
     VÅ¡
    -0.07
    ear
    -0.07
    èĥĨ
    -0.07
    icap
    -0.07
     ÙģرÙĪد
    -0.07
     kå
    -0.07
     onBlur
    -0.07
    blr
    -0.07
    POSITIVE LOGITS
    linger
    0.07
     ('
    0.06
     ("
    0.06
     (“
    0.06
    Ìģ
    0.06
     o
    0.05
    teenth
    0.05
     '
    0.05
     means
    0.05
    æĸĻ
    0.05
    Activations Density 0.047%

    No Known Activations