© 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. 30405
    Prev
    Next
    INDEX
    Explanations

    references related to voting rights and discrimination

    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
     Ãĸn
    -0.07
    getTable
    -0.07
     newfound
    -0.07
     Strap
    -0.07
    igrate
    -0.06
    ipy
    -0.06
    ÏĮ
    -0.06
    /linux
    -0.06
    atter
    -0.06
    (strtolower
    -0.06
    POSITIVE LOGITS
     outdated
    0.08
     currently
    0.06
    utes
    0.06
    enis
    0.06
    Currently
    0.06
     absurd
    0.06
     obstacle
    0.06
     æŃ
    0.06
     still
    0.06
     anomaly
    0.06
    Activations Density 0.038%

    No Known Activations