© 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. 1861
    Prev
    Next
    INDEX
    Explanations

    references to governmental structures and processes related to national security and emergency management

    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
     Rosenstein
    -0.07
    £i
    -0.07
    osl
    -0.06
     Laden
    -0.06
    vil
    -0.06
    otate
    -0.06
    SCII
    -0.06
    .Îķ
    -0.06
    kus
    -0.06
    wake
    -0.06
    POSITIVE LOGITS
    allo
    0.07
    DEM
    0.06
    atif
    0.06
    ListOf
    0.06
    defaultValue
    0.06
     Tib
    0.06
    EqualTo
    0.06
    nia
    0.06
    owell
    0.06
    ĥģ
    0.06
    Activations Density 0.042%

    No Known Activations