© 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. 119730
    Prev
    Next
    INDEX
    Explanations

    concepts related to transcendental and higher purposes in philosophical and spiritual contexts

    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
     Verde
    -0.07
    ниÑĨÑĮ
    -0.06
    itag
    -0.06
     Rapid
    -0.06
     Visual
    -0.06
     McKin
    -0.06
    loff
    -0.06
    ekli
    -0.05
     refresh
    -0.05
    eca
    -0.05
    POSITIVE LOGITS
    ufen
    0.07
    aterno
    0.07
     Gest
    0.07
    atum
    0.07
    ì¶Ķ
    0.07
    té
    0.07
    immer
    0.07
    Äįek
    0.07
    urdy
    0.06
    abbo
    0.06
    Activations Density 0.052%

    No Known Activations