© 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. 88031
    Prev
    Next
    INDEX
    Explanations

    military operations and strategic planning

    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
    celik
    -0.07
    Ñģед
    -0.07
     interp
    -0.07
    .df
    -0.07
     weg
    -0.07
    .LayoutStyle
    -0.07
    è£ģ
    -0.07
    modele
    -0.06
    åĪĢ
    -0.06
    aģı
    -0.06
    POSITIVE LOGITS
     plan
    0.15
    -plan
    0.12
    plan
    0.12
     Plan
    0.11
     operation
    0.11
    Plan
    0.11
     planned
    0.10
     plans
    0.10
    _plan
    0.10
     planning
    0.10
    Activations Density 0.137%

    No Known Activations