© 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. 85917
    Prev
    Next
    INDEX
    Explanations

    expressions related to blessings and religious rituals

    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
    atat
    -0.08
    à¹Ĥà¸ŀ
    -0.07
    anta
    -0.07
    antage
    -0.07
    оÑı
    -0.07
    hausen
    -0.06
    quette
    -0.06
    æ³³
    -0.06
    digest
    -0.06
    ensem
    -0.06
    POSITIVE LOGITS
     Oil
    0.12
     oil
    0.12
     oils
    0.10
    Oil
    0.09
     dầu
    0.08
    æ²¹
    0.07
     oily
    0.07
     applied
    0.07
     petroleum
    0.07
    ÏĦÎŃ
    0.07
    Activations Density 0.004%

    No Known Activations