© 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. 69940
    Prev
    Next
    INDEX
    Explanations

    phrases related to socioeconomic disparities and inequalities

    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
    spath
    -0.07
    andi
    -0.07
    ucch
    -0.07
    asse
    -0.07
     Preferences
    -0.07
    ivo
    -0.06
     dần
    -0.06
    uti
    -0.06
    sgi
    -0.06
     Preference
    -0.06
    POSITIVE LOGITS
     often
    0.12
     typically
    0.11
     generally
    0.11
     usually
    0.10
    often
    0.10
     fewer
    0.09
     Often
    0.09
     souvent
    0.09
    Often
    0.08
     tend
    0.08
    Activations Density 0.042%

    No Known Activations