© 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. 53959
    Prev
    Next
    INDEX
    Explanations

    references to law enforcement and legal contexts

    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
    оÑı
    -0.06
    iva
    -0.06
     sek
    -0.06
    WASHINGTON
    -0.06
    ceae
    -0.06
    zew
    -0.06
    csi
    -0.06
    957
    -0.06
     folded
    -0.06
    upe
    -0.05
    POSITIVE LOGITS
     city
    0.11
     City
    0.10
     municipal
    0.09
    City
    0.09
    .city
    0.08
    -city
    0.08
    city
    0.08
    (city
    0.08
     гоÑĢод
    0.08
     CITY
    0.08
    Activations Density 0.036%

    No Known Activations