© 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. 31305
    Prev
    Next
    INDEX
    Explanations

    references to specific chapters and verses from religious texts, particularly the Bible

    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
    folk
    -0.06
    ãģ°
    -0.06
    aad
    -0.05
    gos
    -0.05
     Sok
    -0.05
    OLF
    -0.05
    tainment
    -0.05
     unders
    -0.05
     ado
    -0.05
    имÑĥ
    -0.05
    POSITIVE LOGITS
    .chapter
    0.08
     chapter
    0.08
    issy
    0.08
    åį·
    0.08
    ushi
    0.08
    andle
    0.08
    #/
    0.07
    anness
    0.07
    RenderingContext
    0.07
    رÙĪØ·
    0.07
    Activations Density 0.006%

    No Known Activations