© 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. 89859
    Prev
    Next
    INDEX
    Explanations

    references to reusable foodware and related environmental initiatives

    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
    aal
    -0.07
    icina
    -0.07
    amina
    -0.07
    fusion
    -0.07
    ragment
    -0.07
    à¸Ľà¸£à¸°à¸ģ
    -0.07
    massage
    -0.07
    pend
    -0.07
    gon
    -0.06
    pData
    -0.06
    POSITIVE LOGITS
     plastic
    0.08
     alternatives
    0.07
     Plastic
    0.07
     ban
    0.07
    zer
    0.07
     gre
    0.07
     replacements
    0.06
     gradual
    0.06
     replacing
    0.06
     global
    0.06
    Activations Density 0.004%

    No Known Activations