© 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. 78410
    Prev
    Next
    INDEX
    Explanations

    themes related to generational characteristics and aspirations

    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
    kova
    -0.08
    umpy
    -0.07
    assen
    -0.07
    Transformation
    -0.07
    ucas
    -0.07
     ******************************************************************************↵
    -0.07
     à¤ľà¤¨à¤¤
    -0.06
    ater
    -0.06
    materials
    -0.06
    itional
    -0.06
    POSITIVE LOGITS
     unlike
    0.07
     world
    0.06
    errat
    0.06
     коммÑĥ
    0.06
     inherit
    0.06
     demands
    0.06
     demanding
    0.06
    omat
    0.06
     Attribution
    0.06
     Ler
    0.06
    Activations Density 0.011%

    No Known Activations