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. 44034
    Prev
    Next
    INDEX
    Explanations

    mathematical terms and definitions related to set theory and order relations

    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
    vala
    -0.07
    olio
    -0.07
    anus
    -0.07
    itches
    -0.06
     FormData
    -0.06
     гаÑĢ
    -0.06
     koc
    -0.06
    åΏ
    -0.06
    anagan
    -0.06
    anny
    -0.06
    POSITIVE LOGITS
     ordering
    0.15
     order
    0.14
     relation
    0.14
     preorder
    0.14
     orders
    0.14
     Ordering
    0.13
     relations
    0.13
     Order
    0.12
     partial
    0.12
     Relation
    0.12
    Activations Density 0.035%

    No Known Activations