Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 31-LLAMASCOPE-RES-131K
    6. 11477
    Prev
    Next
    INDEX
    Explanations

    topics related to ethnicity and race in social contexts

    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
    acias
    -0.06
    imit
    -0.06
    بات
    -0.06
    adaki
    -0.05
    kovou
    -0.05
    alus
    -0.05
    substr
    -0.05
    IMIT
    -0.05
    _OBJC
    -0.05
     vip
    -0.05
    POSITIVE LOGITS
     question
    0.13
     questionnaire
    0.13
     questions
    0.13
     checkboxes
    0.12
     responses
    0.12
     checkbox
    0.12
     answers
    0.12
     tick
    0.11
     Question
    0.11
    responses
    0.11
    Activations Density 0.016%

    No Known Activations