© 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. 84011
    Prev
    Next
    INDEX
    Explanations

    financial and fundraising information related to political campaigns

    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
    Äł
    -0.08
    ιακ
    -0.08
    orra
    -0.08
     mastur
    -0.07
     eskort
    -0.07
    tÃŃ
    -0.07
    _vc
    -0.07
    burger
    -0.07
    ota
    -0.07
    Ëĺ
    -0.07
    POSITIVE LOGITS
     campaign
    0.09
     district
    0.08
     primary
    0.08
     campaigns
    0.07
     Campaign
    0.07
     Primary
    0.07
    primary
    0.07
     incumbent
    0.06
     opponent
    0.06
    -primary
    0.06
    Activations Density 0.073%

    No Known Activations