© 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. 104316
    Prev
    Next
    INDEX
    Explanations

    terms associated with cybersecurity and its vulnerabilities

    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
    ava
    -0.06
     oÄį
    -0.06
    abb
    -0.06
     neod
    -0.06
    enced
    -0.06
     Heck
    -0.06
    aurant
    -0.06
    unal
    -0.06
    ắc
    -0.06
     spd
    -0.06
    POSITIVE LOGITS
    lexport
    0.07
    uitka
    0.07
    èľľ
    0.07
    å¾Ĵ
    0.06
    /rss
    0.06
    emachine
    0.06
    /goto
    0.06
    Disposition
    0.06
     Riverside
    0.06
    StateChanged
    0.06
    Activations Density 0.004%

    No Known Activations