© 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. 1269
    Prev
    Next
    INDEX
    Explanations

    words related to usability and functionality issues

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

    Misspelled words with incorrect letter sequences that disrupt the proper spelling of common English words.

    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
    ,
    -0.07
    .Ag
    -0.06
    488
    -0.06
     Ä
    -0.06
    lyn
    -0.06
    گاÙĨ
    -0.06
     ÃĶ
    -0.06
     Schwartz
    -0.06
    berman
    -0.06
    afc
    -0.05
    POSITIVE LOGITS
    ÌĨ
    0.13
    theless
    0.11
    gether
    0.11
    0.09
    redients
    0.09
    bidden
    0.09
    ÑįÑĤомÑĥ
    0.09
    etheless
    0.09
    bsolute
    0.09
    jourd
    0.09
    Activations Density 0.109%

    No Known Activations