© 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. 54475
    Prev
    Next
    INDEX
    Explanations

    instances of the word "the"

    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
    Ð¡Ðł
    -0.08
    æĶĿ
    -0.07
    erland
    -0.07
    erdale
    -0.07
     -*
    -0.07
    ìĿ´ìŀIJ
    -0.07
     thá»ķ
    -0.07
    eree
    -0.07
     #__
    -0.07
    zeigen
    -0.07
    POSITIVE LOGITS
    amping
    0.06
     m
    0.05
    anks
    0.05
    asio
    0.05
    s
    0.05
    mes
    0.05
    chn
    0.05
    gm
    0.05
    /fwlink
    0.05
    ties
    0.05
    Activations Density 0.032%

    No Known Activations