© 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. 94448
    Prev
    Next
    INDEX
    Explanations

    terms related to online gaming or virtual environments

    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
    rides
    -0.06
    owl
    -0.06
    ç¬
    -0.06
    PCODE
    -0.06
    arya
    -0.06
    åį·
    -0.06
    otta
    -0.06
    æk
    -0.06
    Process
    -0.06
     Scroll
    -0.06
    POSITIVE LOGITS
     Reb
    0.06
     cryst
    0.06
    onia
    0.06
    ResourceId
    0.06
    yna
    0.06
    ulin
    0.06
    .nlm
    0.06
    à¥Ĥल
    0.06
    agu
    0.06
    worth
    0.06
    Activations Density 0.000%

    No Known Activations