© 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. 1231
    Prev
    Next
    INDEX
    Explanations

    phrases related to international cooperation and discussions in space activities

    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
    eka
    -0.07
    assel
    -0.07
    SEA
    -0.06
    roach
    -0.06
    sea
    -0.06
    $MESS
    -0.06
     Bauer
    -0.06
    oven
    -0.06
    strom
    -0.06
     示
    -0.06
    POSITIVE LOGITS
    ÏĥÏĦαν
    0.07
    lech
    0.07
    946
    0.07
     Transcript
    0.07
    687
    0.07
    ê°IJ
    0.07
    AlmostEqual
    0.06
    kening
    0.06
    ACHI
    0.06
    INCT
    0.06
    Activations Density 0.001%

    No Known Activations