© 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. 30682
    Prev
    Next
    INDEX
    Explanations

    phrases related to different ways of living and lifestyle choices

    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
    umo
    -0.06
    controls
    -0.06
    ords
    -0.06
    vr
    -0.06
    icas
    -0.06
    \CMS
    -0.06
    erus
    -0.06
    odo
    -0.06
    æ¥
    -0.06
    ÑĢан
    -0.06
    POSITIVE LOGITS
     lives
    0.15
     life
    0.14
     Lives
    0.12
     жизни
    0.10
     жизнÑĮ
    0.09
     życ
    0.09
    life
    0.09
    _life
    0.09
     vita
    0.09
     vida
    0.08
    Activations Density 0.092%

    No Known Activations