© 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. 15-LLAMASCOPE-RES-131K
    11. 87470
    Prev
    Next
    INDEX
    Explanations

    words indicating relationship or reference, particularly with "which" and "where"

    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
    migration
    -0.07
    kee
    -0.07
    ague
    -0.07
    irth
    -0.06
    ť
    -0.06
     einem
    -0.06
    uvre
    -0.06
    322
    -0.06
    rophic
    -0.06
    ense
    -0.06
    POSITIVE LOGITS
     they
    0.07
     nó
    0.06
     Beam
    0.06
     it
    0.06
     these
    0.06
    MAC
    0.06
    onian
    0.06
    acios
    0.06
    tsky
    0.06
     Yug
    0.06
    Activations Density 0.011%

    No Known Activations