© 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. 2121
    Prev
    Next
    INDEX
    Explanations

    references to divine attributes and characteristics

    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
    üre
    -0.07
    empl
    -0.07
    æĤŁ
    -0.07
    à¹ģรà¸ĩ
    -0.07
    obbies
    -0.07
    udas
    -0.07
    enties
    -0.06
    xdd
    -0.06
    >Last
    -0.06
    _Generic
    -0.06
    POSITIVE LOGITS
     hab
    0.07
     sanat
    0.06
    elm
    0.06
     whom
    0.06
    ubs
    0.06
     Morav
    0.06
     maj
    0.06
     sovereign
    0.06
    .backward
    0.06
    ìĦŃ
    0.06
    Activations Density 0.026%

    No Known Activations