© 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. 62648
    Prev
    Next
    INDEX
    Explanations

    phrases related to disability and compensation

    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
    eten
    -0.07
    ÙģÙĪ
    -0.07
    olid
    -0.06
     GPLv
    -0.06
    _migration
    -0.06
    áme
    -0.06
     eth
    -0.06
    ull
    -0.06
    wik
    -0.06
     sage
    -0.06
    POSITIVE LOGITS
     disability
    0.07
    ÑĢÑĥб
    0.07
    icular
    0.07
    .spin
    0.07
    TTY
    0.07
     -*-č↵
    0.06
     aks
    0.06
    zial
    0.06
     Ù¾ÙĪØ´
    0.06
     unemployment
    0.06
    Activations Density 0.003%

    No Known Activations