© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 117116
    Prev
    Next
    INDEX
    Explanations

    references to religious gatherings and their significance

    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
    apan
    -0.08
    alama
    -0.07
    chn
    -0.07
    @nate
    -0.07
    erten
    -0.07
    GRES
    -0.07
    دÛĮ
    -0.07
    allen
    -0.07
    atatype
    -0.07
    etik
    -0.07
    POSITIVE LOGITS
     Peter
    0.09
     Joel
    0.08
    Peter
    0.07
     Acts
    0.06
     ACT
    0.06
     Matthias
    0.06
     Barn
    0.06
    empo
    0.06
     Bal
    0.06
    opies
    0.06
    Activations Density 0.005%

    No Known Activations