© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 89535
    Prev
    Next
    INDEX
    Explanations

    punctuation, sentence transitions, and narrative markers

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

    Punctuation marks that conclude sentences or paragraphs, often signaling the end of a narrative segment or introducing a transition to a new idea or speaker.

    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
    wers
    -0.08
    astes
    -0.07
     اÙĦرÙħزÙĬØ©
    -0.07
    .isSuccess
    -0.07
    baum
    -0.07
    wf
    -0.07
    sein
    -0.07
    ÅĻÃŃž
    -0.07
    stoff
    -0.07
    ERS
    -0.06
    POSITIVE LOGITS
     story
    0.09
     during
    0.09
     backstory
    0.08
     when
    0.07
     happened
    0.07
     Story
    0.07
    story
    0.07
     details
    0.07
     STORY
    0.07
    istory
    0.06
    Activations Density 0.051%

    No Known Activations