© 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. 73156
    Prev
    Next
    INDEX
    Explanations

    the mention of the United Nations

    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
    мп
    -0.06
     rh
    -0.06
    inger
    -0.06
     Platt
    -0.06
    .builders
    -0.06
    ORK
    -0.06
    aper
    -0.06
    .GetSize
    -0.06
    ware
    -0.06
    AINED
    -0.06
    POSITIVE LOGITS
     Yesterday
    0.07
    Yesterday
    0.07
    ebin
    0.07
    altung
    0.06
    ointment
    0.06
    esk
    0.06
    ä¸Ģç§į
    0.06
     tomorrow
    0.06
     Today
    0.06
    ariate
    0.06
    Activations Density 0.000%

    No Known Activations