© 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. 55021
    Prev
    Next
    INDEX
    Explanations

    references to naval-related terminology or concepts

    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
    å®ħ
    -0.07
    OperationException
    -0.07
    ëŁ
    -0.07
    ç£
    -0.07
    enville
    -0.07
    ì§ľ
    -0.07
    Ùħار
    -0.06
    wich
    -0.06
     Squad
    -0.06
    елÑİ
    -0.06
    POSITIVE LOGITS
    /nav
    0.08
    ieri
    0.07
     Kem
    0.07
    anford
    0.06
    TestClass
    0.06
     Yard
    0.06
    OpenGL
    0.06
     Mev
    0.06
    lsi
    0.06
    Sharper
    0.06
    Activations Density 0.007%

    No Known Activations