© 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. 123902
    Prev
    Next
    INDEX
    Explanations

    references to pigeons or dove-related terminology

    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
    leo
    -0.07
    kening
    -0.07
    addock
    -0.07
    bbie
    -0.07
    ffee
    -0.07
    eneg
    -0.07
     tiener
    -0.07
    _EVT
    -0.07
    rays
    -0.06
    ermal
    -0.06
    POSITIVE LOGITS
    ett
    0.07
    ette
    0.07
     Rockefeller
    0.07
     pigeon
    0.07
    tail
    0.07
    ONS
    0.07
    etti
    0.07
    angel
    0.06
    ettes
    0.06
    elfast
    0.06
    Activations Density 0.005%

    No Known Activations