© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 31115
    Prev
    Next
    INDEX
    Explanations

    references to geopolitical actions and alliances

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     patriotic
    -0.07
    elli
    -0.06
     patriot
    -0.06
    loth
    -0.06
    stÅĻed
    -0.06
    ãĤ¥
    -0.06
     tiener
    -0.06
    ingroup
    -0.06
    groupid
    -0.06
    pector
    -0.06
    POSITIVE LOGITS
     intervention
    0.08
     relations
    0.07
     aid
    0.07
    kup
    0.07
     interventions
    0.07
     assistance
    0.07
     withdrawal
    0.07
     supporting
    0.07
     presence
    0.07
    relations
    0.06
    Activations Density 0.082%

    No Known Activations