© 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. 83562
    Prev
    Next
    INDEX
    Explanations

    references to jewelry and its significance in relationships and events

    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
     aunt
    -0.09
     fian
    -0.08
     uncle
    -0.07
    oldt
    -0.07
    udev
    -0.07
    wed
    -0.07
     Aunt
    -0.06
    ίν
    -0.06
     granny
    -0.06
    dorf
    -0.06
    POSITIVE LOGITS
     son
    0.22
     sons
    0.21
     grandson
    0.20
     daughter
    0.19
     granddaughter
    0.19
     daughters
    0.18
     grandchildren
    0.18
     Son
    0.16
     Sons
    0.16
    Son
    0.16
    Activations Density 0.124%

    No Known Activations