© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 104122
    Prev
    Next
    INDEX
    Explanations

    terms related to independence or autonomy

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    jing
    -0.09
     CreateTable
    -0.08
    AZE
    -0.08
    ëĭ´
    -0.07
    dash
    -0.07
    ToProps
    -0.07
    inne
    -0.07
     Engel
    -0.07
     Bucc
    -0.07
     klu
    -0.07
    POSITIVE LOGITS
     independent
    0.09
     Independent
    0.08
    -minded
    0.07
     independently
    0.07
     spirit
    0.07
     weather
    0.07
     minded
    0.06
    antly
    0.06
    /un
    0.06
     cor
    0.06
    Activations Density 0.026%

    No Known Activations