© 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. 15-LLAMASCOPE-RES-131K
    11. 26561
    Prev
    Next
    INDEX
    Explanations

    French prepositions and articles in context

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

    The French preposition "de" (and its contracted forms "du", "des") connecting noun phrases to indicate possession, origin, quantity or other grammatical relationships in French text.

    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
    land
    -0.08
    ness
    -0.08
    raison
    -0.08
    ìĿĦ
    -0.08
    n
    -0.08
    r
    -0.07
    ed
    -0.07
     nouve
    -0.07
    ly
    -0.07
    anou
    -0.07
    POSITIVE LOGITS
    ffer
    0.07
    ibel
    0.07
    eing
    0.07
    eyh
    0.07
    ocha
    0.07
    ÑĹÑħ
    0.06
    بÙĪاسطة
    0.06
    ores
    0.06
    ighth
    0.06
    yonel
    0.06
    Activations Density 0.040%

    No Known Activations