© 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. 76452
    Prev
    Next
    INDEX
    Explanations

    phrases related to discrimination and equality

    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
    ÑĤин
    -0.08
    amil
    -0.07
    žit
    -0.07
    ingroup
    -0.07
    ojÃŃ
    -0.07
    eyi
    -0.07
    женÑĮ
    -0.07
    PÅĻi
    -0.07
     모ëijIJ
    -0.07
     Rosenstein
    -0.07
    POSITIVE LOGITS
     or
    0.07
    ado
    0.06
     whether
    0.06
    æĺ¯åIJ¦
    0.06
     alone
    0.06
     lack
    0.06
     conscience
    0.06
     merely
    0.06
     perceived
    0.06
     observ
    0.05
    Activations Density 0.009%

    No Known Activations