© 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. 4184
    Prev
    Next
    INDEX
    Explanations

    terms related to social support systems and governmental assistance

    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
    hoot
    -0.07
    suppress
    -0.07
    kova
    -0.07
    inker
    -0.07
    _tc
    -0.07
    imson
    -0.07
     ÑģмеÑĢÑĤÑĮ
    -0.07
     Sür
    -0.07
    nown
    -0.07
    stanov
    -0.07
    POSITIVE LOGITS
     Job
    0.09
    /job
    0.08
     job
    0.07
     unemployed
    0.07
    Job
    0.07
     employ
    0.07
     unemployment
    0.07
     employment
    0.06
    -job
    0.06
     Employment
    0.06
    Activations Density 0.015%

    No Known Activations