© 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. 103852
    Prev
    Next
    INDEX
    Explanations

    concepts related to legal systems and their societal impact

    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
     board
    -0.05
     smoke
    -0.05
    _python
    -0.05
    ,
    -0.05
    AAAA
    -0.05
     prosecution
    -0.05
     komun
    -0.05
    elan
    -0.05
     cof
    -0.05
     sinking
    -0.05
    POSITIVE LOGITS
    -law
    0.14
     law
    0.12
    Law
    0.12
    law
    0.12
    æ³ķ
    0.11
     Law
    0.11
     LAW
    0.10
     hukuk
    0.10
     Legal
    0.10
    legal
    0.09
    Activations Density 0.019%

    No Known Activations