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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 15977
    Prev
    Next
    INDEX
    Explanations

    references to categories and discussions about literature related to disabilities and marginalized groups

    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
    Context
    -0.07
     contextual
    -0.06
    cad
    -0.06
     reference
    -0.06
     complete
    -0.06
    zi
    -0.06
    headline
    -0.06
     Fu
    -0.06
    ̧
    -0.05
    ND
    -0.05
    POSITIVE LOGITS
    人åı£
    0.07
    subclass
    0.07
    /MPL
    0.07
     ún
    0.07
         č↵
    0.07
    etection
    0.07
    _trees
    0.07
    istrovstvÃŃ
    0.07
    rowsable
    0.07
    nia
    0.07
    Activations Density 0.001%

    No Known Activations