© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 103598
    Prev
    Next
    INDEX
    Explanations

    references to affirmative action and diversity policies

    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
    isure
    -0.08
     Nicholson
    -0.07
    AGMA
    -0.07
     ZemÄĽ
    -0.07
    arden
    -0.07
    AMAGE
    -0.06
    unks
    -0.06
    LIKELY
    -0.06
    NullException
    -0.06
     itemprop
    -0.06
    POSITIVE LOGITS
     diversity
    0.08
     Diversity
    0.08
     divers
    0.07
    ews
    0.07
     sensitivity
    0.07
     affirmative
    0.06
    aws
    0.06
     minority
    0.06
     discrimination
    0.06
     Wheels
    0.06
    Activations Density 0.162%

    No Known Activations