© 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. 14199
    Prev
    Next
    INDEX
    Explanations

    complex relational dynamics and conflicts within narratives

    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
    ucc
    -0.08
    -any
    -0.07
    iggers
    -0.07
    ãģŀ
    -0.07
    any
    -0.06
    ÃŃ
    -0.06
    olland
    -0.06
    folk
    -0.06
    geme
    -0.06
    ÙĬ
    -0.06
    POSITIVE LOGITS
     sebuah
    0.12
     several
    0.11
    ä¸Ģ个
    0.11
    æŁIJ
    0.11
     certain
    0.10
     two
    0.10
     some
    0.09
    çļĦä¸Ģ个
    0.09
     einer
    0.09
     one
    0.09
    Activations Density 0.009%

    No Known Activations