© 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. 73709
    Prev
    Next
    INDEX
    Explanations

    variations of the word 'sort'

    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
    egers
    -0.07
    hot
    -0.07
    aters
    -0.07
    zier
    -0.07
    uled
    -0.07
    orum
    -0.06
    errat
    -0.06
    ùng
    -0.06
    RowAt
    -0.06
    hab
    -0.06
    POSITIVE LOGITS
     Hub
    0.07
    alim
    0.07
     out
    0.07
    /filter
    0.07
    tps
    0.06
     ÙĪص
    0.06
    ngo
    0.06
     sort
    0.06
     hub
    0.06
    /platform
    0.06
    Activations Density 0.004%

    No Known Activations