© 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. 86383
    Prev
    Next
    INDEX
    Explanations

    phrases related to teaching and spiritual guidance

    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
    unas
    -0.07
    天åłĤ
    -0.07
    quette
    -0.06
    uber
    -0.06
    æ¿
    -0.06
    ologically
    -0.06
    _OBJC
    -0.06
    éĻĨ
    -0.06
    ichel
    -0.06
    ober
    -0.06
    POSITIVE LOGITS
     unto
    0.10
    vail
    0.07
    jos
    0.07
     Ide
    0.07
     ide
    0.07
    nings
    0.06
    ialect
    0.06
     ид
    0.06
     Colt
    0.06
    iasm
    0.06
    Activations Density 0.298%

    No Known Activations