© 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 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. 59190
    Prev
    Next
    INDEX
    Explanations

    references to digital access and cybersecurity

    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
    iser
    -0.07
    ILING
    -0.07
     FRIEND
    -0.06
    ÙĬÙĪÙĨ
    -0.06
     nÃło
    -0.06
    ιαν
    -0.06
    å¾³
    -0.06
    eling
    -0.06
    qu
    -0.06
    .DependencyInjection
    -0.06
    POSITIVE LOGITS
     sensitive
    0.09
    ensitive
    0.07
     files
    0.07
     secrets
    0.07
     keys
    0.07
     secret
    0.07
    -sensitive
    0.07
    Sensitive
    0.07
     documents
    0.06
     file
    0.06
    Activations Density 0.009%

    No Known Activations