© 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 EvalsExportsAPI 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. 93955
    Prev
    Next
    INDEX
    Explanations

    references to economic growth and job creation

    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
    arez
    -0.06
    ãĥĥãĤ«ãĥ¼
    -0.06
    forman
    -0.06
    alte
    -0.06
    uhe
    -0.06
    byn
    -0.06
    arious
    -0.06
    ):?>↵
    -0.06
    igkeit
    -0.06
    rikes
    -0.06
    POSITIVE LOGITS
     rate
    0.23
     Rate
    0.21
    Rate
    0.20
    rate
    0.19
     rates
    0.18
     RATE
    0.18
    _rate
    0.17
     Rates
    0.17
    -rate
    0.17
    .rate
    0.17
    Activations Density 0.147%

    No Known Activations