© 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. 42010
    Prev
    Next
    INDEX
    Explanations

    references to cybersecurity measures and systems

    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
    achel
    -0.07
    éļĽ
    -0.06
    XS
    -0.06
    STER
    -0.06
    egg
    -0.06
     intermedi
    -0.06
     bead
    -0.06
    entine
    -0.06
    ãĥ©ãĤ¹
    -0.06
    ahr
    -0.06
    POSITIVE LOGITS
     loads
    0.08
     Loads
    0.08
     power
    0.07
     thy
    0.07
     ph
    0.07
     load
    0.07
    )__
    0.07
     IEEE
    0.07
    Loads
    0.07
    eload
    0.07
    Activations Density 0.013%

    No Known Activations