© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 104450
    Prev
    Next
    INDEX
    Explanations

    phrases and punctuation marks that indicate lists or examples in a text

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

    Commas used as punctuation marks in non-English texts (primarily Latin-based languages like French, Spanish, Portuguese, and Italian), often separating clauses or items in lists.

    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
    ÑĮ
    -0.07
     junior
    -0.06
    ulpt
    -0.06
    ennie
    -0.06
     ju
    -0.06
    altar
    -0.06
    qi
    -0.06
    unas
    -0.06
    uzzi
    -0.06
     Reign
    -0.06
    POSITIVE LOGITS
    YLE
    0.08
    æŃ£
    0.07
    ÙĦÙĬÙĩ
    0.07
    ipse
    0.07
    pon
    0.07
    ose
    0.07
    mazon
    0.07
    å®ľ
    0.07
    andom
    0.07
     PartialView
    0.07
    Activations Density 0.104%

    No Known Activations