© 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. 14416
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Eve" or related terms indicating the arrival of events or holidays

    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
    llib
    -0.09
    ãģıãĤĵ
    -0.07
     æĺ¥
    -0.07
    arpa
    -0.06
    avir
    -0.06
    way
    -0.06
    isable
    -0.06
    inz
    -0.06
    erval
    -0.06
    ument
    -0.06
    POSITIVE LOGITS
    ishly
    0.07
    -night
    0.07
    rens
    0.06
    اÙĨÙĩ
    0.06
    ighb
    0.06
    ender
    0.06
    ire
    0.06
    Å¡nÃŃ
    0.06
    endale
    0.06
    entials
    0.06
    Activations Density 0.003%

    No Known Activations