© 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 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. 57430
    Prev
    Next
    INDEX
    Explanations

    references to ethnicity and demographic groups in specific locations

    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
    uta
    -0.07
    bnb
    -0.07
    oltip
    -0.07
    nett
    -0.07
    bons
    -0.07
    osa
    -0.07
    fty
    -0.07
    illac
    -0.07
    Gram
    -0.07
    å§ij
    -0.07
    POSITIVE LOGITS
     Thornton
    0.07
     em
    0.06
    ãi
    0.06
     Salem
    0.06
     Mes
    0.06
     reflective
    0.06
     backgrounds
    0.06
     generic
    0.06
     overst
    0.06
     Clair
    0.06
    Activations Density 0.017%

    No Known Activations