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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 22-LLAMASCOPE-RES-131K
    11. 4231
    Prev
    Next
    INDEX
    Explanations

    references to disability rights and related legislative acts

    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
    933
    -0.09
    .cgi
    -0.07
    orman
    -0.07
    848
    -0.07
    932
    -0.06
    obel
    -0.06
    592
    -0.06
    imary
    -0.06
    pill
    -0.06
    632
    -0.06
    POSITIVE LOGITS
     ADA
    0.11
     accessibility
    0.10
     Accessibility
    0.10
     Americans
    0.10
     inaccessible
    0.09
    Accessible
    0.09
     accessible
    0.09
    ADA
    0.09
    accessible
    0.09
    Americans
    0.08
    Activations Density 0.011%

    No Known Activations