© 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. 59906
    Prev
    Next
    INDEX
    Explanations

    references to electoral manipulation and voting processes

    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
     regs
    -0.07
    mans
    -0.07
    idon
    -0.06
    pell
    -0.06
    ocking
    -0.06
    tiny
    -0.06
    ebo
    -0.06
    ScrollIndicator
    -0.06
     even
    -0.06
    arin
    -0.06
    POSITIVE LOGITS
     approximately
    0.07
    approximately
    0.07
    ĶĦ
    0.07
    ola
    0.07
    iyah
    0.06
     "`
    0.06
     stol
    0.06
    यन
    0.06
    idente
    0.06
    夫人
    0.06
    Activations Density 0.001%

    No Known Activations