© 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. 71732
    Prev
    Next
    INDEX
    Explanations

    the occurrences of the word "ou" and its variations in context

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

    The token "ou" appearing in French text or specialized terminology, particularly as part of proper nouns, technical terms like "Liouville", or common French words.

    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
    ni
    -0.08
    nis
    -0.07
    avan
    -0.07
    ë¶
    -0.07
    ools
    -0.07
    (IService
    -0.07
    ëĭ´
    -0.07
    nesia
    -0.07
    ål
    -0.07
    nic
    -0.07
    POSITIVE LOGITS
    tright
    0.07
    verture
    0.07
    thern
    0.07
    illet
    0.07
    ville
    0.07
    liers
    0.06
    e
    0.06
    illard
    0.06
    jours
    0.06
    ever
    0.06
    Activations Density 0.040%

    No Known Activations