© 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. 9-LLAMASCOPE-RES-131K
    11. 94274
    Prev
    Next
    INDEX
    Explanations

    references to additives and preservatives in beverages

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     defer
    -0.07
    665
    -0.07
    tek
    -0.06
    534
    -0.06
    atron
    -0.06
    ÙĪع
    -0.06
    348
    -0.06
    orgh
    -0.06
    ppy
    -0.06
    à¹Īà¸Ńà¸Ļ
    -0.06
    POSITIVE LOGITS
    dB
    0.07
     nth
    0.06
    oso
    0.06
    _excerpt
    0.06
     Chavez
    0.06
    izza
    0.06
    isma
    0.06
    Enumerator
    0.06
     detect
    0.06
    NECT
    0.06
    Activations Density 0.004%

    No Known Activations