© 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. 86930
    Prev
    Next
    INDEX
    Explanations

    references to political messaging and rallying calls

    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
    urat
    -0.07
    uze
    -0.07
    enko
    -0.07
    unky
    -0.07
     diplom
    -0.07
    lexport
    -0.07
    eydi
    -0.07
    -sur
    -0.07
    zman
    -0.06
     democrat
    -0.06
    POSITIVE LOGITS
    win
    0.07
     platform
    0.06
     winning
    0.06
     Fitzgerald
    0.06
     leadership
    0.06
     ÙĪسط
    0.06
     pitch
    0.06
    ickets
    0.06
     campaign
    0.06
    WIN
    0.06
    Activations Density 0.021%

    No Known Activations