© 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. 15-LLAMASCOPE-RES-131K
    11. 87802
    Prev
    Next
    INDEX
    Explanations

    concepts related to living out Christian values and teachings

    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
    obi
    -0.07
    usher
    -0.06
     burden
    -0.06
    oba
    -0.06
     Holt
    -0.06
     z
    -0.06
     buried
    -0.06
    eding
    -0.06
     Lambert
    -0.06
     symptom
    -0.06
    POSITIVE LOGITS
     everyday
    0.09
     daily
    0.09
    .scalablytyped
    0.08
     УкÑĢаÑĹ
    0.07
    daily
    0.07
     wherever
    0.07
     é¡
    0.07
    úsqueda
    0.07
    ĥn
    0.07
    emon
    0.07
    Activations Density 0.029%

    No Known Activations