© 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. 81928
    Prev
    Next
    INDEX
    Explanations

    references to political exploitation or opportunism during crises

    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
    indered
    -0.06
    utschein
    -0.06
     rebellion
    -0.06
     Modified
    -0.06
    leasing
    -0.06
    .parallel
    -0.06
     DISPATCH
    -0.06
    erset
    -0.06
     Parallel
    -0.06
     Bubble
    -0.06
    POSITIVE LOGITS
     politics
    0.09
     political
    0.09
     opportun
    0.08
    political
    0.07
     Political
    0.07
     opport
    0.07
     politic
    0.07
     Politics
    0.07
     полиÑĤ
    0.07
     polÃŃtica
    0.07
    Activations Density 0.034%

    No Known Activations