© 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. 108888
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to time and dates

    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
    éli
    -0.07
    üss
    -0.06
    _SECURE
    -0.06
    ãi
    -0.06
    акон
    -0.06
    inkle
    -0.06
     zd
    -0.06
    ouns
    -0.06
    rys
    -0.06
    .lambda
    -0.06
    POSITIVE LOGITS
    visor
    0.07
    179
    0.07
    bow
    0.07
     galleries
    0.07
     Lay
    0.06
    adian
    0.06
     gallery
    0.06
    داÙĨ
    0.06
    ارد
    0.06
    isk
    0.06
    Activations Density 0.016%

    No Known Activations