© 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. 42251
    Prev
    Next
    INDEX
    Explanations

    references to interfaith dialogue and religious cooperation

    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
    ä
    -0.07
     &
    -0.07
     somebody
    -0.06
     Vak
    -0.06
    ansa
    -0.06
     substant
    -0.06
     early
    -0.06
     shit
    -0.06
     everybody
    -0.06
     Rev
    -0.06
    POSITIVE LOGITS
     deleg
    0.08
    laden
    0.07
    iÅŁ
    0.07
     suche
    0.07
    },{↵
    0.07
    ections
    0.07
    oÄŁ
    0.07
    ipeg
    0.07
    phanumeric
    0.07
    ittle
    0.07
    Activations Density 0.003%

    No Known Activations