© 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. 70013
    Prev
    Next
    INDEX
    Explanations

    words related to socioeconomic status and class distinctions

    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
    eron
    -0.07
    angkan
    -0.07
    %C
    -0.07
    aldi
    -0.07
     Ner
    -0.07
    ¤ëĭ¤
    -0.06
    outu
    -0.06
    unte
    -0.06
    okino
    -0.06
    oro
    -0.06
    POSITIVE LOGITS
     folk
    0.09
    人ãģ¯
    0.09
     же
    0.08
     folks
    0.08
     też
    0.07
    人ãģĮ
    0.07
     bunu
    0.07
    759
    0.07
     ìĤ¬ëŀĮìĿĢ
    0.07
    주ëĬĶ
    0.07
    Activations Density 0.056%

    No Known Activations