© 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. 38273
    Prev
    Next
    INDEX
    Explanations

    proper nouns and references to specific individuals and entities in political 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
    imore
    -0.06
    eel
    -0.06
     Hen
    -0.06
    pek
    -0.06
    .extensions
    -0.06
    uster
    -0.06
    .splitext
    -0.06
    loven
    -0.06
     баг
    -0.05
    oze
    -0.05
    POSITIVE LOGITS
     dangers
    0.10
     danger
    0.10
     Danger
    0.10
    eware
    0.10
    ä¸įè¦ģ
    0.09
     rằng
    0.08
     about
    0.08
     bahwa
    0.07
     against
    0.07
    .warn
    0.07
    Activations Density 0.009%

    No Known Activations