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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 38749
    Prev
    Next
    INDEX
    Explanations

    phrases that convey excitement or anticipation regarding new experiences or introductions

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

    Punctuation and introductory phrases that signal content transitions, particularly when introducing new topics, people, or entities to the reader.

    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
    ushima
    -0.07
    ÙĬÙĤ
    -0.06
    umar
    -0.06
    Enums
    -0.06
     thÆ°
    -0.06
    .enum
    -0.06
    .enums
    -0.06
    /includes
    -0.06
    utter
    -0.06
    caster
    -0.06
    POSITIVE LOGITS
     introduce
    0.19
     introdu
    0.19
     introduction
    0.19
     introduced
    0.18
     introduces
    0.17
     introducing
    0.16
     Introduction
    0.14
     Introduced
    0.14
     Meet
    0.14
    roducing
    0.14
    Activations Density 0.080%

    No Known Activations