© 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. 9-LLAMASCOPE-RES-131K
    11. 96258
    Prev
    Next
    INDEX
    Explanations

    strategic concepts and techniques in various contexts, particularly related to games or systems

    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
     phóng
    -0.08
    .lucene
    -0.08
     минÑĥ
    -0.08
    lacak
    -0.08
    jspx
    -0.07
     кÑĥлÑĮÑĤÑĥ
    -0.07
    digital
    -0.07
    spender
    -0.07
    icaret
    -0.07
    wart
    -0.07
    POSITIVE LOGITS
     pros
    0.06
    oi
    0.06
     tip
    0.06
     strategy
    0.06
     suck
    0.05
     tes
    0.05
     Pill
    0.05
     Carry
    0.05
     strategies
    0.05
     hack
    0.05
    Activations Density 0.004%

    No Known Activations