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. 43552
    Prev
    Next
    INDEX
    Explanations

    symbols or characters that may denote mathematical or scientific variables

    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
     SwiftUI
    -0.07
     Fortnite
    -0.06
     manufacturer
    -0.06
    analyze
    -0.06
    /chart
    -0.06
     manufacturers
    -0.06
     Renault
    -0.05
     shoppers
    -0.05
     customers
    -0.05
     Apple
    -0.05
    POSITIVE LOGITS
     Conservation
    0.16
     conservation
    0.15
     Philippines
    0.12
     Philippine
    0.12
     Filipino
    0.11
     Wildlife
    0.10
     NGO
    0.10
     CL
    0.10
     biodiversity
    0.10
     wildlife
    0.10
    Activations Density 0.003%

    No Known Activations