© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 129966
    Prev
    Next
    INDEX
    Explanations

    discussions around electoral fraud claims and related political controversies

    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
    lass
    -0.08
    ãĤ«ãĥ«
    -0.07
    輯
    -0.07
    ickou
    -0.07
    Ã¼ÅŁ
    -0.07
    quia
    -0.07
    ůj
    -0.07
    _CHIP
    -0.07
    Trivia
    -0.06
    bpp
    -0.06
    POSITIVE LOGITS
     recounts
    0.09
     contested
    0.08
     fraud
    0.08
     recount
    0.08
     Fraud
    0.07
     Die
    0.07
     irregular
    0.07
     Election
    0.07
    oxetine
    0.07
     counting
    0.07
    Activations Density 0.195%

    No Known Activations