© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 16947
    Prev
    Next
    INDEX
    Explanations

    phrases related to political actions and sentiments regarding President Trump and the Republican Party

    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
    باÙĨ
    -0.07
    kün
    -0.07
    otti
    -0.07
    ektor
    -0.07
    ehir
    -0.07
    .opensource
    -0.07
    typeorm
    -0.07
    avaÅŁ
    -0.07
     пÑĢеÑģÑĤ
    -0.07
    onder
    -0.07
    POSITIVE LOGITS
     grid
    0.09
     obstruction
    0.08
    grid
    0.07
     House
    0.07
     Grid
    0.07
     bills
    0.06
    Grid
    0.06
    ouse
    0.06
     compromise
    0.06
    akis
    0.06
    Activations Density 0.059%

    No Known Activations