© 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. 57024
    Prev
    Next
    INDEX
    Explanations

    athletic performance statistics and achievements

    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
    aptive
    -0.08
    idente
    -0.07
    ourg
    -0.07
    insky
    -0.07
    Ø´Ùĩ
    -0.06
    .Îł
    -0.06
    elper
    -0.06
    oose
    -0.06
    ipment
    -0.06
     rode
    -0.06
    POSITIVE LOGITS
     Tig
    0.06
     vind
    0.06
    бол
    0.06
    ovat
    0.06
     Cop
    0.06
    pac
    0.06
     ÙħÙĪÙĦ
    0.06
     Mig
    0.05
    rape
    0.05
     Hag
    0.05
    Activations Density 0.018%

    No Known Activations