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

    Neuronpedia

    Jacobian LensNEW
    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. 119315
    Prev
    Next
    INDEX
    Explanations

    references to modern societal issues and challenges

    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
    ansen
    -0.07
    inya
    -0.07
    ativ
    -0.06
    akk
    -0.06
    tep
    -0.06
    ENTE
    -0.06
    anton
    -0.06
    ills
    -0.06
     Flo
    -0.06
    Ø·Ùĩ
    -0.06
    POSITIVE LOGITS
     world
    0.11
     environment
    0.11
     society
    0.09
     times
    0.08
     ìĦ¸ìĥģ
    0.08
     environments
    0.08
    çݯå¢ĥ
    0.08
     миÑĢе
    0.07
     landscape
    0.07
     ortam
    0.07
    Activations Density 0.026%

    No Known Activations