© 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. 80819
    Prev
    Next
    INDEX
    Explanations

    scientific terms and concepts related to cancer research

    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
    datagrid
    -0.07
     interpol
    -0.07
    iffe
    -0.07
    datatable
    -0.07
     vidé
    -0.07
     ontvangst
    -0.06
    egas
    -0.06
    erview
    -0.06
     راÛĮ
    -0.06
    åħ½
    -0.06
    POSITIVE LOGITS
    research
    0.07
    acic
    0.07
     research
    0.07
     researching
    0.07
     researchers
    0.07
     изÑĥÑĩ
    0.07
    boom
    0.07
     study
    0.07
    çłĶ究
    0.06
     cell
    0.06
    Activations Density 0.010%

    No Known Activations