© 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. 27741
    Prev
    Next
    INDEX
    Explanations

    expressions of pride or being proud

    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
    onth
    -0.07
    alem
    -0.07
    ÙĬات
    -0.07
     unders
    -0.06
    oad
    -0.06
     Francois
    -0.06
    279
    -0.06
    lap
    -0.06
    elu
    -0.06
    oth
    -0.06
    POSITIVE LOGITS
    (er
    0.08
    ness
    0.07
    bery
    0.07
    lier
    0.07
     enough
    0.07
    OfFile
    0.07
    iful
    0.07
     of
    0.06
    ippo
    0.06
    errer
    0.06
    Activations Density 0.005%

    No Known Activations