© 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. 1174
    Prev
    Next
    INDEX
    Explanations

    phrases related to political discourse and negotiations

    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
    EditMode
    -0.06
     clim
    -0.06
    ÅĻÃŃzenÃŃ
    -0.06
    aeda
    -0.06
    ailable
    -0.06
    AtA
    -0.06
    DECL
    -0.06
    otti
    -0.06
     Ortiz
    -0.06
    opup
    -0.06
    POSITIVE LOGITS
     Nuclear
    0.07
     monitoring
    0.07
     monitors
    0.07
     nuclear
    0.07
    IOC
    0.07
     Monitoring
    0.06
     arms
    0.06
    gest
    0.06
     Arms
    0.06
     restart
    0.06
    Activations Density 0.005%

    No Known Activations