© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 29962
    Prev
    Next
    INDEX
    Explanations

    expressions related to team success and progress in sports contexts

    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
    uition
    -0.07
    izu
    -0.07
    vik
    -0.07
    mage
    -0.07
    uten
    -0.07
    AGMA
    -0.07
    ofi
    -0.07
     ká»ĭp
    -0.06
     Synd
    -0.06
     Bris
    -0.06
    POSITIVE LOGITS
     already
    0.10
     Already
    0.10
    already
    0.09
     guaranteed
    0.09
    Already
    0.09
    secure
    0.09
     secure
    0.08
    å·²ç»ı
    0.08
     secured
    0.08
    _already
    0.08
    Activations Density 0.055%

    No Known Activations