© 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. 31359
    Prev
    Next
    INDEX
    Explanations

    specific nautical terms related to lighthouses and their characteristics

    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
    verb
    -0.06
    275
    -0.06
     Watt
    -0.06
    pk
    -0.05
     Ange
    -0.05
     oceans
    -0.05
    лод
    -0.05
    elman
    -0.05
     dint
    -0.05
     AMA
    -0.05
    POSITIVE LOGITS
    Destructor
    0.08
    adero
    0.08
    _ENC
    0.07
    ắt
    0.07
     خدÙħات
    0.07
    леж
    0.07
    .Designer
    0.07
     toItem
    0.07
    amment
    0.07
    unsafe
    0.07
    Activations Density 0.003%

    No Known Activations