© 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 EvalsExportsinterp-engineNEWAPI 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. 73135
    Prev
    Next
    INDEX
    Explanations

    instances of the word "dem" or its variants, indicating a focus on themes related to democracy or democratic principles

    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
    heim
    -0.08
    achs
    -0.08
    osity
    -0.07
     hé
    -0.07
    igm
    -0.07
    sd
    -0.07
    holes
    -0.07
    idf
    -0.07
    ÏįÏĢ
    -0.07
    anford
    -0.06
    POSITIVE LOGITS
     dem
    0.09
     Dem
    0.08
    ographics
    0.07
    214
    0.07
    íĻ
    0.07
    Dem
    0.07
    ned
    0.06
     DEM
    0.06
     Decomp
    0.06
    dem
    0.06
    Activations Density 0.014%

    No Known Activations