© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 89784
    Prev
    Next
    INDEX
    Explanations

    references to internet domains and associated security measures

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
     hacking
    -0.06
    ниÑĨÑĭ
    -0.06
    ActivityResult
    -0.06
    _ADAPTER
    -0.06
    ubbo
    -0.06
    èĶµ
    -0.06
     ÙħÙħÙĨ
    -0.06
     PROCUREMENT
    -0.06
     Reconstruction
    -0.06
     nir
    -0.05
    POSITIVE LOGITS
     servers
    0.07
     server
    0.07
    ayan
    0.07
     služ
    0.07
     service
    0.07
    yne
    0.07
     services
    0.06
    .cloudflare
    0.06
     cloud
    0.06
    èħķ
    0.06
    Activations Density 0.020%

    No Known Activations