© 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 EvalsExportsinterp-engineNEWAPI 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. 54718
    Prev
    Next
    INDEX
    Explanations

    phrases related to spiritual practice and liberation

    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
    yr
    -0.06
    ILT
    -0.06
    URNS
    -0.06
    ets
    -0.06
    ëħ
    -0.06
    ungan
    -0.06
    bai
    -0.06
    urre
    -0.06
    reon
    -0.06
     kin
    -0.05
    POSITIVE LOGITS
     Cousins
    0.07
    ãĥ«ãĥķ
    0.07
    åŁ
    0.07
    ç´Ķ
    0.07
     hrd
    0.07
     totalement
    0.07
     Gand
    0.07
    .RightToLeft
    0.07
    ãĥ¼ãĥľ
    0.06
    ä¸ĭ载次æķ°
    0.06
    Activations Density 0.008%

    No Known Activations