© 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. 86468
    Prev
    Next
    INDEX
    Explanations

    claims of superiority and self-perception regarding intelligence

    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
    اÙĦÙĬا
    -0.07
    arious
    -0.07
    æĬķ注
    -0.07
     кÑĥлÑĮ
    -0.07
    kova
    -0.07
    ogui
    -0.06
    uib
    -0.06
    IALIZED
    -0.06
    erli
    -0.06
    RSS
    -0.06
    POSITIVE LOGITS
     superior
    0.09
     entitled
    0.08
     superiority
    0.08
     entitlement
    0.07
     victim
    0.07
     Alone
    0.07
     unique
    0.06
    åĩĮ
    0.06
     everyone
    0.06
     special
    0.06
    Activations Density 0.037%

    No Known Activations