© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 61700
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and their varied usage in text

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

    Punctuation marks (primarily periods) that conclude quotations or statements from authority figures in formal writing.

    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
    Ùħز
    -0.07
    pac
    -0.07
    åĨ
    -0.06
    ighbor
    -0.06
    emap
    -0.06
    434
    -0.06
    ìn
    -0.06
    ditor
    -0.06
    íĥ
    -0.06
    à¸ķล
    -0.06
    POSITIVE LOGITS
     indeed
    0.10
     Indeed
    0.08
    Indeed
    0.08
    nesc
    0.07
     himself
    0.07
    oÄŁ
    0.06
    888
    0.06
    EGA
    0.06
    828
    0.06
     diplom
    0.06
    Activations Density 0.058%

    No Known Activations