© 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. 116590
    Prev
    Next
    INDEX
    Explanations

    concepts related to public-private partnerships and the associated outcomes

    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
     Sabb
    -0.08
    SEG
    -0.07
    绣
    -0.07
    ¥IJ
    -0.07
     æ¥Ń
    -0.06
     ÑĤиÑħ
    -0.06
     ad
    -0.06
    ilian
    -0.06
    tractor
    -0.06
    Gratis
    -0.06
    POSITIVE LOGITS
    ju
    0.06
     risks
    0.06
    émon
    0.06
     funds
    0.06
     risk
    0.06
     health
    0.06
    ile
    0.06
    grim
    0.06
     funding
    0.06
    health
    0.06
    Activations Density 0.001%

    No Known Activations