© 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. 103880
    Prev
    Next
    INDEX
    Explanations

    references to Arctic sea ice and its changes

    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
    ANGE
    -0.06
     Bosch
    -0.06
    ctest
    -0.06
     Starter
    -0.06
     rainfall
    -0.06
    vens
    -0.06
     eiusmod
    -0.06
     Pais
    -0.06
    jer
    -0.06
    ropp
    -0.06
    POSITIVE LOGITS
     ice
    0.09
     Blob
    0.08
     melting
    0.08
     Arctic
    0.08
     rings
    0.07
     assim
    0.07
     Ice
    0.07
     circ
    0.07
    کت
    0.06
     Alaska
    0.06
    Activations Density 0.010%

    No Known Activations