© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 116439
    Prev
    Next
    INDEX
    Explanations

    expressions related to the concept of justice and evaluation

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    æ³ķ人
    -0.07
    ÑĥÑĪки
    -0.07
    ued
    -0.07
    yre
    -0.06
     affid
    -0.06
    Ñĥди
    -0.06
    hoff
    -0.06
    ypress
    -0.06
    ÙĪبÛĮ
    -0.06
    دÙĪد
    -0.06
    POSITIVE LOGITS
     justice
    0.20
     Justice
    0.16
    justice
    0.16
    Justice
    0.14
     injustice
    0.13
     fairness
    0.11
     fair
    0.10
     injust
    0.09
     unfair
    0.09
     Fair
    0.08
    Activations Density 0.067%

    No Known Activations