© 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. 39692
    Prev
    Next
    INDEX
    Explanations

    references to job roles and employment conditions

    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
    uran
    -0.07
    ohon
    -0.06
     -
    -0.06
    à¸ļล
    -0.06
     –
    -0.06
     engel
    -0.06
     -,
    -0.05
    testCase
    -0.05
    alf
    -0.05
    isson
    -0.05
    POSITIVE LOGITS
    upa
    0.07
    edly
    0.07
    ина
    0.06
     indirect
    0.06
    icia
    0.06
    á»ijng
    0.06
    коÑĤ
    0.06
     prezident
    0.06
     spol
    0.06
    atura
    0.06
    Activations Density 0.000%

    No Known Activations