© 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. 53723
    Prev
    Next
    INDEX
    Explanations

    phrases related to adherence to rules and regulations

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    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
    ogi
    -0.07
    nee
    -0.07
     éĩİ
    -0.07
    ãĥ¼ãĥĵ
    -0.07
    hood
    -0.06
    rats
    -0.06
    rif
    -0.06
    /Area
    -0.06
     Huff
    -0.06
     Linh
    -0.06
    POSITIVE LOGITS
     rules
    0.10
     standards
    0.09
     strict
    0.09
     principles
    0.08
     conventions
    0.08
    Rules
    0.07
    bris
    0.07
     norms
    0.07
     ìĤ¬íķŃ
    0.07
     strictly
    0.07
    Activations Density 0.019%

    No Known Activations