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. 43656
    Prev
    Next
    INDEX
    Explanations

    symbols and terms related to religious or cultural concepts

    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
     Industrial
    -0.07
     industrial
    -0.06
     National
    -0.06
    chwitz
    -0.06
     Hawth
    -0.06
    ocaust
    -0.06
     Industry
    -0.06
     NATIONAL
    -0.06
     industry
    -0.06
     industries
    -0.06
    POSITIVE LOGITS
     royal
    0.10
     kings
    0.10
     monarchy
    0.09
    elite
    0.09
     ruler
    0.09
     elite
    0.09
     elites
    0.09
     dyn
    0.09
    roy
    0.09
     ritual
    0.09
    Activations Density 0.010%

    No Known Activations