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. 43705
    Prev
    Next
    INDEX
    Explanations

    themes of complex relationships and family dynamics

    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
    .inflate
    -0.07
    Inflater
    -0.06
    ÑĢаÑĤи
    -0.05
    -bs
    -0.05
    valuator
    -0.05
     inefficient
    -0.05
    лами
    -0.05
    .rd
    -0.05
    vatel
    -0.05
    werk
    -0.05
    POSITIVE LOGITS
     remar
    0.15
     divor
    0.15
     divorce
    0.15
     divorced
    0.14
     desert
    0.12
     married
    0.12
     marrying
    0.11
     marriage
    0.10
     marry
    0.10
     deserted
    0.10
    Activations Density 0.094%

    No Known Activations