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

    Neuronpedia

    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. 71869
    Prev
    Next
    INDEX
    Explanations

    references to personal relationships and social interactions

    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
    egin
    -0.09
    assi
    -0.07
    erna
    -0.07
    431
    -0.07
    posable
    -0.07
    aka
    -0.07
    esh
    -0.07
    adena
    -0.06
    Alternatively
    -0.06
     бÑĥдÑĮ
    -0.06
    POSITIVE LOGITS
     recently
    0.07
     several
    0.07
    æŁIJ
    0.07
     particular
    0.06
    çļĦä¸Ģ个
    0.06
    ãģ¾ãĤĭ
    0.06
     hadn
    0.06
    ẹn
    0.06
     áll
    0.06
    @js
    0.06
    Activations Density 0.038%

    No Known Activations