© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 28627
    Prev
    Next
    INDEX
    Explanations

    references to underrepresented minority groups in the context of educational opportunities

    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
    WithOptions
    -0.06
     [|
    -0.06
    /catalog
    -0.06
     preferredStyle
    -0.06
    aceous
    -0.06
    ÏĦεÏį
    -0.06
    inesis
    -0.06
     Sı
    -0.06
     figsize
    -0.06
    imentary
    -0.06
    POSITIVE LOGITS
    Phys
    0.06
    apa
    0.06
     representation
    0.06
    iteral
    0.06
    erca
    0.06
    ode
    0.06
    Ana
    0.06
     REPRESENT
    0.06
    ãĥ§
    0.06
     reclaimed
    0.06
    Activations Density 0.004%

    No Known Activations