© 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. 78510
    Prev
    Next
    INDEX
    Explanations

    information related to electoral processes and candidate requirements

    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
    assy
    -0.07
     handjob
    -0.06
     Spieler
    -0.06
    iska
    -0.06
     Parliamentary
    -0.06
    zÃŃ
    -0.06
     tournaments
    -0.06
    ania
    -0.06
    -ext
    -0.06
     prive
    -0.06
    POSITIVE LOGITS
     local
    0.07
    positions
    0.07
     positions
    0.07
    ToLocal
    0.07
     District
    0.07
     district
    0.07
     Local
    0.07
    _local
    0.06
     locally
    0.06
     bids
    0.06
    Activations Density 0.015%

    No Known Activations