© 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. 69038
    Prev
    Next
    INDEX
    Explanations

    references to governmental organizations and their departments

    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
    vrier
    -0.08
    iÄįky
    -0.07
    memberof
    -0.07
    orsi
    -0.07
    SharedPointer
    -0.07
    egie
    -0.07
     Demp
    -0.06
    ami
    -0.06
    ÅĻeh
    -0.06
    alm
    -0.06
    POSITIVE LOGITS
    .nih
    0.08
    .gov
    0.08
     Division
    0.08
     National
    0.07
     Bureau
    0.07
     division
    0.07
     US
    0.07
    Division
    0.07
     Office
    0.07
     Federal
    0.06
    Activations Density 0.037%

    No Known Activations