© 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. 86696
    Prev
    Next
    INDEX
    Explanations

    terms related to accessibility and assistance for individuals with disabilities

    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
    ripe
    -0.07
    ÑĢÑĥÑĪ
    -0.07
    POSIT
    -0.07
    aq
    -0.06
    appa
    -0.06
    SSIP
    -0.06
    iben
    -0.06
    icana
    -0.06
    isz
    -0.06
     jich
    -0.06
    POSITIVE LOGITS
    abled
    0.10
     disabilities
    0.08
     disabled
    0.07
     Peaks
    0.07
     disability
    0.07
     DISABLE
    0.07
     accom
    0.07
     Disabilities
    0.07
     Disabled
    0.07
     accommodation
    0.06
    Activations Density 0.006%

    No Known Activations