© 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. 18504
    Prev
    Next
    INDEX
    Explanations

    references to antisemitism and related conspiracy theories

    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
    irez
    -0.08
    Prostit
    -0.07
    PropertyDescriptor
    -0.07
    implify
    -0.07
    egin
    -0.07
    .EventType
    -0.07
    ìĹ
    -0.06
     demokrat
    -0.06
     Aç
    -0.06
    figcaption
    -0.06
    POSITIVE LOGITS
     vir
    0.08
     offline
    0.07
     fringe
    0.07
    isms
    0.06
     reg
    0.06
     Rep
    0.06
    AZY
    0.06
     Ident
    0.06
     online
    0.06
     tolerated
    0.06
    Activations Density 0.047%

    No Known Activations