© 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. 31499
    Prev
    Next
    INDEX
    Explanations

    references to natural disasters and their impact

    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
    .InnerException
    -0.09
    INLINE
    -0.09
     znal
    -0.08
    osl
    -0.08
    Ðĭ
    -0.08
    sgi
    -0.07
    ornings
    -0.07
    chez
    -0.07
    EXPORT
    -0.07
    ÃĹ↵↵
    -0.07
    POSITIVE LOGITS
     Saturday
    0.07
    ,
    0.07
     Sunday
    0.06
     care
    0.06
     children
    0.06
     multiple
    0.06
     tail
    0.06
    0.06
     as
    0.06
     (
    0.06
    Activations Density 0.031%

    No Known Activations