© 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. 1582
    Prev
    Next
    INDEX
    Explanations

    names or references associated with the letter "Ay" and its variations

    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
    icum
    -0.07
    adden
    -0.07
    yi
    -0.07
    consistent
    -0.07
    ajÄħ
    -0.07
    avid
    -0.07
    gov
    -0.07
    鼶
    -0.07
    zioni
    -0.07
    egin
    -0.07
    POSITIVE LOGITS
    urved
    0.09
    illary
    0.07
    oub
    0.07
     Swift
    0.06
    ushman
    0.06
    ewitness
    0.06
    áy
    0.06
    ollah
    0.06
    aload
    0.06
    bridge
    0.06
    Activations Density 0.009%

    No Known Activations