© 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. 2943
    Prev
    Next
    INDEX
    Explanations

    phrases associated with voting and voter registration processes

    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
    اعÙĬ
    -0.07
    mland
    -0.07
     Gst
    -0.07
    ÑĢади
    -0.07
    istar
    -0.06
    villa
    -0.06
    ãĥijãĥ³
    -0.06
    wil
    -0.06
    Latch
    -0.06
    ãĥ
    -0.06
    POSITIVE LOGITS
     state
    0.07
    -registration
    0.07
     registration
    0.06
     Registration
    0.06
     Election
    0.06
    .registration
    0.06
    ç±į
    0.06
     State
    0.06
    çĬ¶æĢģ
    0.06
    Registration
    0.06
    Activations Density 0.011%

    No Known Activations