© 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. 6013
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to educational institutions and their goals

    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
    abh
    -0.07
     defer
    -0.06
    ahl
    -0.06
     lam
    -0.06
     Antar
    -0.06
    Asc
    -0.06
    жи
    -0.06
     Fuel
    -0.06
    empo
    -0.06
     ð
    -0.06
    POSITIVE LOGITS
    @nate
    0.07
     Translation
    0.07
     Bened
    0.07
    -medium
    0.06
    .eu
    0.06
    δί
    0.06
    iban
    0.06
    766
    0.06
     اÙĦجاÙħ
    0.06
     european
    0.06
    Activations Density 0.002%

    No Known Activations