© 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. 116676
    Prev
    Next
    INDEX
    Explanations

    references to LGBTQ+ identities, particularly relating to gay communities and relationships

    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
    naire
    -0.08
    lew
    -0.08
    inus
    -0.08
    bjerg
    -0.07
    rál
    -0.07
    ively
    -0.07
    lauf
    -0.07
    erable
    -0.07
    naires
    -0.07
    åĨĮ
    -0.07
    POSITIVE LOGITS
    lord
    0.07
    ness
    0.07
    dar
    0.07
    ì¶ķ
    0.06
    -friendly
    0.06
    yyyy
    0.06
    -themed
    0.06
    ish
    0.06
    sh
    0.06
    bis
    0.06
    Activations Density 0.004%

    No Known Activations