© 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. 30862
    Prev
    Next
    INDEX
    Explanations

    specific references to voting, elections, and civic duties

    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
    omb
    -0.07
    este
    -0.07
    onet
    -0.06
    etter
    -0.06
    ymb
    -0.06
    omi
    -0.05
    oken
    -0.05
    sie
    -0.05
    essian
    -0.05
     Sultan
    -0.05
    POSITIVE LOGITS
     rằng
    0.16
     bahwa
    0.15
     ÏĮÏĦι
    0.14
     how
    0.13
     that
    0.12
     että
    0.12
     že
    0.12
     дека
    0.11
     why
    0.11
     whether
    0.11
    Activations Density 0.097%

    No Known Activations