© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 99283
    Prev
    Next
    INDEX
    Explanations

    words related to pride and its manifestations or implications

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    mod
    -0.07
    rame
    -0.07
    iser
    -0.07
    ssize
    -0.07
    swer
    -0.07
    vey
    -0.07
    isation
    -0.07
    ovice
    -0.07
    rez
    -0.07
    ood
    -0.07
    POSITIVE LOGITS
    fully
    0.09
    ably
    0.08
    åħ¸
    0.07
    ibly
    0.07
    aller
    0.07
    EFR
    0.06
    -io
    0.06
    ovol
    0.06
    Sharper
    0.06
    iful
    0.06
    Activations Density 0.005%

    No Known Activations