© 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. 38289
    Prev
    Next
    INDEX
    Explanations

    expressions of personal identity and creative motivation

    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
    engl
    -0.06
     today
    -0.06
    759
    -0.06
    egl
    -0.06
     conversation
    -0.06
     below
    -0.06
    rib
    -0.06
     Williamson
    -0.06
    ::$
    -0.06
     lunch
    -0.06
    POSITIVE LOGITS
    /Error
    0.08
     nues
    0.07
     GOODMAN
    0.07
    onet
    0.07
     putas
    0.07
    ýv
    0.07
     milfs
    0.06
    aye
    0.06
     Bur
    0.06
     personals
    0.06
    Activations Density 0.000%

    No Known Activations