© 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. 108670
    Prev
    Next
    INDEX
    Explanations

    references to personal growth and self-discovery

    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
    ÅĤu
    -0.07
    ressed
    -0.06
    licht
    -0.06
    æ³ī
    -0.06
    erce
    -0.06
     akci
    -0.06
     lá
    -0.06
    itz
    -0.06
    kas
    -0.06
     Zip
    -0.06
    POSITIVE LOGITS
     learning
    0.09
     trying
    0.09
    Trying
    0.09
     slowly
    0.09
     figuring
    0.08
    learning
    0.08
     Trying
    0.08
     Learning
    0.08
    Learning
    0.08
    trying
    0.08
    Activations Density 0.121%

    No Known Activations