© 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. 15-LLAMASCOPE-RES-131K
    11. 86165
    Prev
    Next
    INDEX
    Explanations

    expressions of doubt and criticism regarding societal views and accountability

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    Discourse markers and transitional phrases that connect ideas, particularly those expressing contrast, qualification, or the introduction of personal viewpoints.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219
    Triggered 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
    Negative Logits
    ullo
    -0.07
    ium
    -0.06
    870
    -0.06
    enu
    -0.06
    outh
    -0.06
    argo
    -0.06
    961
    -0.06
    _VO
    -0.06
     guides
    -0.06
    990
    -0.06
    POSITIVE LOGITS
    gnore
    0.07
    _inverse
    0.07
    trys
    0.07
    antan
    0.07
     ÄĮes
    0.07
    _REF
    0.07
    CJK
    0.07
    mÃŃ
    0.06
    ÑħÑĸд
    0.06
    .Dot
    0.06
    Activations Density 0.023%

    No Known Activations