© 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. 104339
    Prev
    Next
    INDEX
    Explanations

    statements and reports regarding political or military interactions

    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
     Huck
    -0.06
     Alexand
    -0.06
    izu
    -0.06
    actices
    -0.06
    izzie
    -0.06
     numel
    -0.06
    ALS
    -0.06
    endale
    -0.06
    lio
    -0.06
    ObjectId
    -0.06
    POSITIVE LOGITS
     Foreign
    0.08
    Foreign
    0.07
     foreign
    0.07
     United
    0.07
     Äijáp
    0.07
    urances
    0.07
     ministries
    0.06
     imports
    0.06
    678
    0.06
     Blink
    0.06
    Activations Density 0.067%

    No Known Activations