© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 2600
    Prev
    Next
    INDEX
    Explanations

    terms related to military technology and operations

    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
     Airways
    -0.08
     Airlines
    -0.08
     airlines
    -0.08
     airline
    -0.08
    iform
    -0.06
     Bom
    -0.06
    vil
    -0.06
     Rossi
    -0.06
    baum
    -0.06
     Luft
    -0.06
    POSITIVE LOGITS
     vessels
    0.08
     Sensor
    0.07
     Modular
    0.07
    tin
    0.07
     lỼp
    0.07
    æİĴ
    0.07
    åĴ²
    0.07
     vessel
    0.07
    eltas
    0.07
    rones
    0.07
    Activations Density 0.011%

    No Known Activations