© 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. 75942
    Prev
    Next
    INDEX
    Explanations

    phrases related to gaming and player engagement

    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
    .LookAndFeel
    -0.07
     Sanayi
    -0.07
     Essentials
    -0.07
    fuse
    -0.06
    ess
    -0.06
    รà¸ĵ
    -0.06
    Splash
    -0.06
    oogle
    -0.06
    cess
    -0.06
    ardu
    -0.06
    POSITIVE LOGITS
    fon
    0.07
    alie
    0.07
    ừng
    0.07
    ipa
    0.06
     Hodg
    0.06
     zÅĤ
    0.06
    EGA
    0.06
     interfer
    0.06
     Wil
    0.06
    .easing
    0.06
    Activations Density 0.018%

    No Known Activations