© 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. 17439
    Prev
    Next
    INDEX
    Explanations

    terms related to disability advocacy and inclusion

    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
    ëŁī
    -0.07
    ilk
    -0.06
    Fcn
    -0.06
     ethn
    -0.06
     Buen
    -0.06
    enko
    -0.06
    ông
    -0.06
    GPC
    -0.06
    .tar
    -0.06
    ycl
    -0.06
    POSITIVE LOGITS
     disability
    0.15
     disabled
    0.15
     Disabled
    0.14
     Disability
    0.14
    disabled
    0.14
     wheelchair
    0.13
     disabilities
    0.13
    Disabled
    0.13
    -disabled
    0.11
     disable
    0.11
    Activations Density 0.066%

    No Known Activations