© 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 EvalsExportsAPI 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. 60920
    Prev
    Next
    INDEX
    Explanations

    references to sexual identity and orientation

    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
    apiro
    -0.07
    udu
    -0.07
    lung
    -0.06
    ùi
    -0.06
    atori
    -0.06
    olatile
    -0.06
     GetLastError
    -0.06
    illage
    -0.06
     Hashtable
    -0.06
    riba
    -0.06
    POSITIVE LOGITS
    girl
    0.06
    uchs
    0.06
     Census
    0.06
     self
    0.06
     definition
    0.06
     autistic
    0.06
    æ¼
    0.06
    usercontent
    0.06
    TTY
    0.06
    ardo
    0.06
    Activations Density 0.001%

    No Known Activations