© 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 EvalsExportsAPI 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. 3673
    Prev
    Next
    INDEX
    Explanations

    references to the Cold War and nuclear threat

    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
     Blasio
    -0.07
    idar
    -0.07
    StackNavigator
    -0.07
    ãĥĥãĤ«ãĥ¼
    -0.06
     penny
    -0.06
    egrator
    -0.06
     Rescue
    -0.06
    utzer
    -0.06
     Tan
    -0.06
    ependency
    -0.06
    POSITIVE LOGITS
     nuclear
    0.12
     Cold
    0.11
     Russia
    0.10
    Cold
    0.10
     Nuclear
    0.09
    æł¸
    0.09
     Russian
    0.09
    Russia
    0.08
    Russian
    0.08
     Russians
    0.08
    Activations Density 0.113%

    No Known Activations