© 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. 60428
    Prev
    Next
    INDEX
    Explanations

    instances of punctuation or sentence structures

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

    Punctuation marks ending sentences that describe character traits, personality aspects, or behavior patterns in narrative text.

    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
    lek
    -0.08
     yourselves
    -0.07
    rear
    -0.07
    ongyang
    -0.07
    éric
    -0.07
    iguiente
    -0.07
    _shapes
    -0.06
     Duty
    -0.06
    ãn
    -0.06
    fully
    -0.06
    POSITIVE LOGITS
     his
    0.11
     seiner
    0.08
    his
    0.08
    ä»ĸçļĦ
    0.07
     seinem
    0.07
     when
    0.07
     seine
    0.07
     его
    0.07
     sua
    0.07
     suoi
    0.07
    Activations Density 0.051%

    No Known Activations