© 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. 39543
    Prev
    Next
    INDEX
    Explanations

    references to marginalized or economically disadvantaged communities and their struggles

    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
    facet
    -0.07
     Dich
    -0.07
    gii
    -0.07
    urat
    -0.07
    ugins
    -0.07
    amble
    -0.07
    amus
    -0.07
    roz
    -0.07
    ucken
    -0.06
    ÙıÙĦ
    -0.06
    POSITIVE LOGITS
     segment
    0.08
     disproportion
    0.07
     segments
    0.07
    æ¯Ķä¾ĭ
    0.07
     vulnerability
    0.07
    層
    0.07
     participation
    0.07
     tend
    0.07
     disproportionately
    0.06
     rates
    0.06
    Activations Density 0.038%

    No Known Activations