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. 43554
    Prev
    Next
    INDEX
    Explanations

    descriptions of versatile living spaces and practical home design features

    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
     inoc
    -0.06
     whistlebl
    -0.06
     whistleblower
    -0.06
    owering
    -0.06
     protestors
    -0.05
    润
    -0.05
     franchises
    -0.05
     güvenilir
    -0.05
    .cv
    -0.05
    inder
    -0.05
    POSITIVE LOGITS
     flow
    0.11
     circulation
    0.10
     layout
    0.10
     functional
    0.10
     spatial
    0.10
     layouts
    0.10
     functionality
    0.10
     flows
    0.10
     traffic
    0.10
     function
    0.09
    Activations Density 0.025%

    No Known Activations