© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 104341
    Prev
    Next
    INDEX
    Explanations

    mentions of familial relationships, particularly involving husbands and partners

    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
    acters
    -0.08
     Friend
    -0.07
    kke
    -0.07
    illa
    -0.07
    ÑĤаб
    -0.07
    جاج
    -0.06
    opes
    -0.06
    еÑģа
    -0.06
    incinn
    -0.06
    nap
    -0.06
    POSITIVE LOGITS
     Bair
    0.07
     Highlands
    0.06
     Ran
    0.06
     Pier
    0.06
     settled
    0.06
    end
    0.05
    625
    0.05
     downs
    0.05
     gradient
    0.05
     bio
    0.05
    Activations Density 0.007%

    No Known Activations