© 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. 86511
    Prev
    Next
    INDEX
    Explanations

    themes of personal growth and self-improvement

    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
    ÙĪز
    -0.06
     minds
    -0.06
     Voices
    -0.05
    å¬
    -0.05
    upakan
    -0.05
    voices
    -0.05
    suming
    -0.05
    amm
    -0.05
     none
    -0.05
    visor
    -0.05
    POSITIVE LOGITS
     life
    0.30
     Life
    0.24
    life
    0.24
     LIFE
    0.23
    -life
    0.22
    Life
    0.22
     жизни
    0.21
    _life
    0.21
    -Life
    0.19
    .life
    0.19
    Activations Density 0.196%

    No Known Activations