© 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 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. 78477
    Prev
    Next
    INDEX
    Explanations

    themes related to salvation and the afterlife

    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
     Anim
    -0.07
    맥
    -0.07
    HasKey
    -0.06
    eca
    -0.06
    Compat
    -0.06
    esda
    -0.06
    icult
    -0.06
    Animated
    -0.06
    deen
    -0.06
    ราย
    -0.06
    POSITIVE LOGITS
    æ°¸ä¹ħ
    0.07
    ืà¸Ļ
    0.06
     final
    0.06
    cit
    0.06
    æı
    0.06
    abol
    0.06
     Bott
    0.06
     eskort
    0.06
    CLUD
    0.06
     forever
    0.06
    Activations Density 0.008%

    No Known Activations