© 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. 31210
    Prev
    Next
    INDEX
    Explanations

    instances of indefinite articles, particularly emphasizing importance or significance

    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
    olib
    -0.08
    ÙĨج
    -0.08
    apons
    -0.07
    indow
    -0.07
    ãģļ
    -0.07
     dÃŃl
    -0.07
    LEGRO
    -0.06
    otime
    -0.06
    ÑıÑĤи
    -0.06
    ãģ¤
    -0.06
    POSITIVE LOGITS
     history
    0.07
    RT
    0.06
     exceptions
    0.06
     population
    0.06
     motto
    0.06
     scre
    0.06
    êµ´
    0.06
     properly
    0.06
    edith
    0.06
    maz
    0.06
    Activations Density 0.013%

    No Known Activations