© 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. 69296
    Prev
    Next
    INDEX
    Explanations

    statements indicating comparison or contrast

    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
    اخ
    -0.06
     kok
    -0.06
     r
    -0.06
    chin
    -0.06
    702
    -0.06
    (æľĪ
    -0.06
    Creators
    -0.06
    eam
    -0.06
    istas
    -0.06
     Conv
    -0.06
    POSITIVE LOGITS
    _sdk
    0.07
    swick
    0.07
    ccione
    0.07
    iÄħ
    0.07
    827
    0.07
    кÑĤа
    0.07
     Finder
    0.07
    icÃŃ
    0.06
    è©ŀ
    0.06
    AZY
    0.06
    Activations Density 0.004%

    No Known Activations