© 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. 31626
    Prev
    Next
    INDEX
    Explanations

    phrases related to governmental oversight and accountability

    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
     Congress
    -0.11
     congress
    -0.10
     Legislature
    -0.09
    Congress
    -0.08
     legislature
    -0.08
     senator
    -0.08
     Parliament
    -0.08
    ÙĦت
    -0.07
     congressional
    -0.07
    gress
    -0.07
    POSITIVE LOGITS
     executive
    0.07
     Department
    0.07
     witnesses
    0.07
     intelligence
    0.07
     Intelligence
    0.06
     Executive
    0.06
     props
    0.06
     ep
    0.06
    propri
    0.06
     President
    0.06
    Activations Density 0.046%

    No Known Activations