© 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. 106284
    Prev
    Next
    INDEX
    Explanations

    references to issues related to societal norms and justice narratives

    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
     Wikipedia
    -0.08
    âĢ¦↵
    -0.08
    âĢ¦
    -0.06
    byt
    -0.06
    âĢ¦.
    -0.06
    land
    -0.06
     among
    -0.05
     âĢ¦↵
    -0.05
    Ì
    -0.05
     wikipedia
    -0.05
    POSITIVE LOGITS
    ëĮ
    0.09
    riba
    0.08
    èm
    0.07
     اÙĦرÙħزÙĬØ©
    0.07
    OptionsMenu
    0.07
    /*č↵
    0.07
    Äįel
    0.07
    วล
    0.07
    ÃŃÅ¡
    0.07
    .gc
    0.07
    Activations Density 0.065%

    No Known Activations