© 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. 5733
    Prev
    Next
    INDEX
    Explanations

    references to the word "night" and its variations

    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
    agem
    -0.08
    phy
    -0.07
    ühl
    -0.07
    oidal
    -0.07
    oid
    -0.07
    utow
    -0.07
    ddy
    -0.07
    à¸Ļะ
    -0.07
    azo
    -0.07
     nodeName
    -0.07
    POSITIVE LOGITS
    ime
    0.09
    cap
    0.09
    mare
    0.08
    -time
    0.08
    mares
    0.08
    crawler
    0.08
    /day
    0.08
    IME
    0.07
    erif
    0.07
    shade
    0.07
    Activations Density 0.011%

    No Known Activations