© 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. 61392
    Prev
    Next
    INDEX
    Explanations

    references to social responsibility and advocacy for 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
    anel
    -0.08
    eteria
    -0.08
    exus
    -0.07
    uent
    -0.07
    Scalars
    -0.07
    asar
    -0.06
    ledged
    -0.06
    otify
    -0.06
    rzy
    -0.06
    -basket
    -0.06
    POSITIVE LOGITS
     responsibility
    0.08
     responsible
    0.08
     Responsibility
    0.07
     society
    0.07
     communities
    0.07
    896
    0.07
     responsibilities
    0.06
     ourselves
    0.06
    ÏĦαι
    0.06
     Responsibilities
    0.06
    Activations Density 0.034%

    No Known Activations