© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 39995
    Prev
    Next
    INDEX
    Explanations

    references and discussions related to passwords and password 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
    infeld
    -0.09
    ================================================================
    -0.07
    лиÑĨ
    -0.07
    maal
    -0.07
    udget
    -0.06
    wit
    -0.06
    мовÑĸÑĢ
    -0.06
    etro
    -0.06
     Mash
    -0.06
    anness
    -0.06
    POSITIVE LOGITS
    ed
    0.08
    eer
    0.07
    _strength
    0.07
    umed
    0.07
    ned
    0.07
    ock
    0.07
    elmet
    0.07
    ntag
    0.07
    ning
    0.07
    emp
    0.07
    Activations Density 0.006%

    No Known Activations