© 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. 29108
    Prev
    Next
    INDEX
    Explanations

    mentions of systemic issues related to incarceration and racial disparities

    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
    ARRIER
    -0.07
    à¹Ģหà¸Ļ
    -0.07
    indrome
    -0.07
    екÑĤи
    -0.07
    uga
    -0.06
    utilities
    -0.06
     Hed
    -0.06
     Ulus
    -0.06
    stab
    -0.06
     Deluxe
    -0.06
    POSITIVE LOGITS
    olith
    0.08
     racial
    0.07
     scales
    0.07
     harsh
    0.07
     Dra
    0.06
    iesel
    0.06
    ylon
    0.06
    bew
    0.06
    Ñģол
    0.06
     laws
    0.06
    Activations Density 0.020%

    No Known Activations