© 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. 85430
    Prev
    Next
    INDEX
    Explanations

    mentions of electoral policies and their effectiveness

    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
    bÃŃr
    -0.08
    ÏĢα
    -0.07
    λά
    -0.07
    orang
    -0.07
    สาร
    -0.07
    ï¼Ĭ
    -0.07
    swers
    -0.07
     servis
    -0.07
    éĢģæĸĻçĦ¡æĸĻ
    -0.07
    graf
    -0.07
    POSITIVE LOGITS
     average
    0.07
     Nam
    0.06
     Average
    0.06
    671
    0.06
    onder
    0.06
     median
    0.06
    du
    0.06
     nice
    0.06
    k
    0.06
    MK
    0.06
    Activations Density 0.001%

    No Known Activations