© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 117100
    Prev
    Next
    INDEX
    Explanations

    references to LGBTQ+ representation and advocacy

    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
     åĿ
    -0.07
     populist
    -0.07
     lien
    -0.07
    íĨµ
    -0.07
     Neck
    -0.06
     Forg
    -0.06
    ãģ«è¦ĭ
    -0.06
     addCriterion
    -0.06
     helicopt
    -0.06
     swingers
    -0.06
    POSITIVE LOGITS
     LGBT
    0.12
     HIV
    0.12
     gay
    0.12
     queer
    0.11
     LGBTQ
    0.11
     AIDS
    0.11
     rainbow
    0.10
     drag
    0.10
     transgender
    0.09
     Ston
    0.09
    Activations Density 0.240%

    No Known Activations