© 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. 120222
    Prev
    Next
    INDEX
    Explanations

    expressions of enjoyment and fulfillment in work-related activities

    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
    ije
    -0.07
    rlen
    -0.06
    ,<
    -0.06
    Å¡Å¥
    -0.06
    ilia
    -0.06
    leet
    -0.06
    imar
    -0.06
    .pa
    -0.06
    iju
    -0.06
     Barth
    -0.06
    POSITIVE LOGITS
     challenge
    0.07
     satisfaction
    0.07
     challenges
    0.06
     puzzles
    0.06
    ůr
    0.06
    ible
    0.06
    IBLE
    0.06
    enek
    0.06
     aspect
    0.06
     interesting
    0.06
    Activations Density 0.027%

    No Known Activations