© 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. 58484
    Prev
    Next
    INDEX
    Explanations

    references to voter registration and election integrity issues

    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
    panse
    -0.07
    chal
    -0.07
    	Copyright
    -0.07
    hdl
    -0.07
    GraphNode
    -0.07
    Descriptors
    -0.07
    kea
    -0.07
    usercontent
    -0.07
    riad
    -0.06
    getAs
    -0.06
    POSITIVE LOGITS
     lists
    0.09
     list
    0.08
    list
    0.08
     roster
    0.08
     database
    0.07
     List
    0.07
    sis
    0.07
     batch
    0.07
     records
    0.07
     Database
    0.07
    Activations Density 0.033%

    No Known Activations