© 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. 104011
    Prev
    Next
    INDEX
    Explanations

    references to black holes and gravitational waves

    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
    __,__
    -0.07
    .Handled
    -0.07
    ropol
    -0.07
    EGA
    -0.07
     FileAccess
    -0.07
    legen
    -0.07
     LinkedHashMap
    -0.06
    ÄĽtÃŃ
    -0.06
     Bamboo
    -0.06
    uren
    -0.06
    POSITIVE LOGITS
     black
    0.09
     Schwar
    0.08
     Black
    0.08
     inspir
    0.07
    Black
    0.07
    -black
    0.07
    black
    0.07
     iron
    0.07
     BLACK
    0.07
    ystack
    0.07
    Activations Density 0.388%

    No Known Activations