© 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 EvalsExportsAPI 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. 85611
    Prev
    Next
    INDEX
    Explanations

    terms related to voting rights and legislative changes impacting marginalized communities

    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
    ilos
    -0.07
    Policy
    -0.07
     Policy
    -0.07
    _policy
    -0.07
    ako
    -0.06
    ofi
    -0.06
    ystore
    -0.06
    utar
    -0.06
     soap
    -0.06
    ÑĢÑıдÑĥ
    -0.06
    POSITIVE LOGITS
     Voting
    0.09
    é¼
    0.07
    race
    0.06
     voting
    0.06
     ATL
    0.06
     Race
    0.06
     íıIJ
    0.06
    _race
    0.06
    TimeString
    0.06
    udur
    0.06
    Activations Density 0.002%

    No Known Activations