© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 17083
    Prev
    Next
    INDEX
    Explanations

    references to stereotypes and critiques of their impacts

    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
    lier
    -0.08
    ness
    -0.08
    arde
    -0.07
    íģ¼
    -0.07
    rate
    -0.07
    iero
    -0.07
    itation
    -0.07
    elter
    -0.07
    iane
    -0.07
    riel
    -0.06
    POSITIVE LOGITS
    otypical
    0.07
    ically
    0.07
    istical
    0.07
    ENARIO
    0.07
    گر
    0.07
    ëł
    0.06
    éĢļãĤĬ
    0.06
     Ñģобой
    0.06
     Ster
    0.06
    ãĥ¼ãĥĦ
    0.06
    Activations Density 0.006%

    No Known Activations