© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 75521
    Prev
    Next
    INDEX
    Explanations

    discussions surrounding cybersecurity and device safety

    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
    avir
    -0.07
    оÑĢод
    -0.06
    zelf
    -0.06
     xuyên
    -0.06
    206
    -0.06
    odont
    -0.06
    ´
    -0.06
     Fell
    -0.06
    uti
    -0.06
    razier
    -0.06
    POSITIVE LOGITS
     vulnerable
    0.07
     manufacturer
    0.07
     security
    0.07
     manufacturers
    0.07
     insecure
    0.07
    kee
    0.06
    usercontent
    0.06
    .DEFAULT
    0.06
     ì·¨
    0.06
    овеÑĢ
    0.06
    Activations Density 0.008%

    No Known Activations