© 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. 1455
    Prev
    Next
    INDEX
    Explanations

    references to anti-Semitic violence

    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
    éĻ£
    -0.06
     pun
    -0.06
    inally
    -0.06
    ross
    -0.06
    ë²Į
    -0.06
     prison
    -0.06
     grid
    -0.05
    éĺµ
    -0.05
    PropertyName
    -0.05
    ilde
    -0.05
    POSITIVE LOGITS
    Ĺi
    0.07
     Shib
    0.07
     harassed
    0.07
    /Gate
    0.06
    alen
    0.06
     Attacks
    0.06
    .Reporting
    0.06
    ophobia
    0.06
    idden
    0.06
     isolation
    0.06
    Activations Density 0.006%

    No Known Activations