© 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. 17-LLAMASCOPE-RES-131K
    11. 94480
    Prev
    Next
    INDEX
    Explanations

    mentions of relationships and family connections

    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
    riend
    -0.06
     boyfriend
    -0.06
    otts
    -0.06
     adolescence
    -0.06
     elsewhere
    -0.06
     struct
    -0.06
    else
    -0.06
    à¸İ
    -0.06
    头
    -0.06
    ium
    -0.05
    POSITIVE LOGITS
     produce
    0.08
     produces
    0.07
     producing
    0.07
    .nih
    0.07
    çĶ£
    0.07
    âĶĺ
    0.07
     Produ
    0.07
    γά
    0.07
    _usb
    0.07
    stÃŃ
    0.07
    Activations Density 0.020%

    No Known Activations