© 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. 9-LLAMASCOPE-RES-131K
    11. 98625
    Prev
    Next
    INDEX
    Explanations

    terms related to religious or theological concepts

    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
    iq
    -0.06
    _topology
    -0.06
    iggers
    -0.06
    erus
    -0.06
    860
    -0.06
    еÑĢеÑĩ
    -0.06
    869
    -0.06
    628
    -0.06
     Subset
    -0.06
    icha
    -0.06
    POSITIVE LOGITS
    گاÙĨ
    0.07
    /fa
    0.06
    pha
    0.06
     اÙĦز
    0.06
    jezd
    0.06
    ryn
    0.06
     MSD
    0.06
    uta
    0.06
    à¸Łà¸£
    0.06
    hd
    0.06
    Activations Density 0.031%

    No Known Activations