© 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. 76521
    Prev
    Next
    INDEX
    Explanations

    concepts related to equality and fairness in societal contexts

    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
    oste
    -0.07
    riad
    -0.07
    olo
    -0.07
     SPDX
    -0.06
    olon
    -0.06
    altar
    -0.06
    ante
    -0.06
    éĴ®
    -0.06
     âĹĦ
    -0.06
    ülü
    -0.06
    POSITIVE LOGITS
     equal
    0.23
     equally
    0.20
    equal
    0.19
     Equal
    0.19
     igual
    0.19
    Equal
    0.18
     EQUAL
    0.18
     eÅŁit
    0.16
     equality
    0.16
    _equal
    0.15
    Activations Density 0.196%

    No Known Activations