© 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. 90773
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and symbols related to quotes or dialogue

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

    Punctuation marks that serve a structural role in sentences, often appearing between clauses, phrases or list items. Most commonly commas, parentheses, quotation marks, or hyphens that join related content, establish boundaries between ideas, or denote relationships between sentence elements.

    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
    /people
    -0.07
    uko
    -0.07
    μοί
    -0.07
    qa
    -0.07
    .sponge
    -0.07
    езд
    -0.07
    еди
    -0.07
     qa
    -0.07
    cam
    -0.07
    ilig
    -0.06
    POSITIVE LOGITS
     the
    0.10
     certain
    0.08
     a
    0.07
    dden
    0.07
     any
    0.07
    ropy
    0.07
    aban
    0.07
     those
    0.06
     The
    0.06
    ceptar
    0.06
    Activations Density 0.029%

    No Known Activations