© 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. 90884
    Prev
    Next
    INDEX
    Explanations

    prepositions and articles in a text

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

    The token "der" appears as a frequent German article often used within phrases indicating attribution, location, or membership, typically preceding nouns in prepositional phrases like "in der" (in the) or referring to institutional affiliations.

    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
    ea
    -0.07
    SelectionMode
    -0.07
    ey
    -0.06
    rax
    -0.06
    cctor
    -0.06
    sst
    -0.06
    verte
    -0.06
    etz
    -0.06
    aled
    -0.06
    cket
    -0.06
    POSITIVE LOGITS
    ly
    0.09
    że
    0.08
    zeit
    0.07
    оÑĥ
    0.07
    ÃŃo
    0.07
    ials
    0.07
    anza
    0.07
    >:</
    0.07
    æ°ı
    0.07
    znik
    0.07
    Activations Density 0.011%

    No Known Activations