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. 43481
    Prev
    Next
    INDEX
    Explanations

    special characters and symbols, possibly indicating scientific or mathematical notation

    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
     religions
    -0.07
     religion
    -0.07
     mankind
    -0.07
     Religion
    -0.06
     Jehovah
    -0.06
     Jeh
    -0.06
     superst
    -0.05
     Apollo
    -0.05
     STRICT
    -0.05
     Happiness
    -0.05
    POSITIVE LOGITS
    Ep
    0.08
     Episcopal
    0.07
     Pres
    0.07
     resilience
    0.07
     Wilmington
    0.07
     ministry
    0.07
     Ep
    0.07
     vulner
    0.07
     Adaptive
    0.07
     contextual
    0.07
    Activations Density 0.004%

    No Known Activations