© 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. 17753
    Prev
    Next
    INDEX
    Explanations

    terms related to demographics and their analysis

    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
    ews
    -0.07
    ãĥĥãĥĦ
    -0.06
    rollback
    -0.06
    رش
    -0.06
     rollback
    -0.06
    ountries
    -0.06
    este
    -0.06
    pty
    -0.06
    lete
    -0.06
    vá
    -0.06
    POSITIVE LOGITS
    defgroup
    0.07
    Population
    0.07
     Population
    0.07
    ALE
    0.07
     ÐĿаÑģеление
    0.06
    egl
    0.06
    uele
    0.06
    adero
    0.06
    ÙĪÛĮÙĨ
    0.06
     جÙħعÛĮت
    0.06
    Activations Density 0.001%

    No Known Activations