© 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. 18628
    Prev
    Next
    INDEX
    Explanations

    references to the Times of Israel and quotations from individuals

    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
    änn
    -0.08
     اÙĦÙħد
    -0.08
    ormsg
    -0.07
    ssc
    -0.07
    ÏģιÏĥ
    -0.07
    quil
    -0.07
    mys
    -0.07
    Ý
    -0.07
     Mandal
    -0.07
    emand
    -0.07
    POSITIVE LOGITS
     count
    0.07
    unos
    0.07
     av
    0.06
     port
    0.06
     later
    0.06
     Av
    0.06
     cult
    0.06
     Hash
    0.06
     Porter
    0.06
     Tub
    0.06
    Activations Density 0.009%

    No Known Activations