© 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. 130027
    Prev
    Next
    INDEX
    Explanations

    phrases related to planning and strategic decision-making

    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
    é³
    -0.08
    wald
    -0.07
    ebek
    -0.07
    acier
    -0.07
    寿
    -0.07
    ascus
    -0.07
     Orig
    -0.07
    elon
    -0.07
    .ua
    -0.07
    .ToDateTime
    -0.06
    POSITIVE LOGITS
     implementation
    0.07
     starting
    0.07
     starters
    0.07
     Implementation
    0.07
     starter
    0.07
    -start
    0.07
     Phase
    0.06
     IMPLEMENT
    0.06
    START
    0.06
     cultural
    0.06
    Activations Density 0.001%

    No Known Activations