© 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. 30278
    Prev
    Next
    INDEX
    Explanations

    terms related to cybersecurity and technology roles

    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
    iros
    -0.08
     sublic
    -0.08
    amax
    -0.07
    oard
    -0.07
    fillType
    -0.07
    submenu
    -0.07
    atorium
    -0.07
    /GPL
    -0.07
    /assert
    -0.07
     GOODMAN
    -0.07
    POSITIVE LOGITS
     federal
    0.08
     IT
    0.07
     Federal
    0.07
     Cabinet
    0.07
     vendor
    0.07
     DC
    0.07
     Department
    0.07
     procure
    0.07
    gov
    0.07
    pell
    0.06
    Activations Density 0.017%

    No Known Activations