© 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. 124164
    Prev
    Next
    INDEX
    Explanations

    names or titles related to individuals, particularly those of South Asian descent

    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
    Enumerator
    -0.08
    ippets
    -0.08
    prung
    -0.07
    errupted
    -0.07
    ODB
    -0.07
    jee
    -0.07
    roker
    -0.07
    ERG
    -0.07
    chia
    -0.07
    uju
    -0.07
    POSITIVE LOGITS
    eb
    0.06
    azzi
    0.06
    estic
    0.06
    ee
    0.06
    à¥įà¤ŀ
    0.06
    n
    0.06
     speeding
    0.06
    um
    0.06
    ness
    0.06
    تÙħاع
    0.06
    Activations Density 0.009%

    No Known Activations