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

    Neuronpedia

    Jacobian LensNEW
    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. 78508
    Prev
    Next
    INDEX
    Explanations

    words and phrases associated with weddings and marriage

    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
    acz
    -0.07
    ınca
    -0.06
     dwell
    -0.06
    ãģĻãģIJ
    -0.06
    rega
    -0.06
     पड
    -0.06
    senal
    -0.06
    .showMessage
    -0.06
    à¸ķร
    -0.06
     Husband
    -0.06
    POSITIVE LOGITS
    Ư
    0.07
    yar
    0.07
    erman
    0.07
    rip
    0.06
     tomorrow
    0.06
     postponed
    0.06
    ityEngine
    0.06
    ieren
    0.06
    elay
    0.06
    thesis
    0.06
    Activations Density 0.016%

    No Known Activations