© 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. 53746
    Prev
    Next
    INDEX
    Explanations

    phrases related to procedural or bureaucratic actions 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
    ridge
    -0.07
    ارد
    -0.07
    ashi
    -0.07
    endale
    -0.07
    amera
    -0.06
    ¤
    -0.06
    antine
    -0.06
    YPRE
    -0.06
    isis
    -0.06
    ãĥªãĥ¼
    -0.06
    POSITIVE LOGITS
    -Sah
    0.07
     foreign
    0.06
     slightest
    0.06
    culate
    0.06
     the
    0.06
     Ged
    0.06
    oste
    0.06
     tempt
    0.06
     amount
    0.06
     exact
    0.06
    Activations Density 0.024%

    No Known Activations