© 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. 123620
    Prev
    Next
    INDEX
    Explanations

    any mention of same-sex marriage and LGBTQ+ rights

    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
    Bear
    -0.07
    eller
    -0.06
    cri
    -0.06
     McDon
    -0.06
     ver
    -0.06
     Bear
    -0.06
     improvised
    -0.06
     ÙĤدر
    -0.05
     Butler
    -0.05
     accr
    -0.05
    POSITIVE LOGITS
     Exclusive
    0.11
    Exclusive
    0.11
     VIDEO
    0.11
     exclusive
    0.11
    exclusive
    0.10
    -video
    0.09
    VIDEO
    0.09
     video
    0.09
    -exclusive
    0.09
     Opinion
    0.08
    Activations Density 0.147%

    No Known Activations