© 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. 82301
    Prev
    Next
    INDEX
    Explanations

    pronouns and references to individuals in discussions about government actions or policies

    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
    ابÛĮ
    -0.06
     Py
    -0.06
    TEL
    -0.06
     Dud
    -0.06
    γÏģάÏĨ
    -0.06
    CSR
    -0.06
     py
    -0.06
    æ¥
    -0.06
    rey
    -0.06
    say
    -0.06
    POSITIVE LOGITS
     sẽ
    0.09
     WILL
    0.09
     will
    0.09
    will
    0.09
    'll
    0.07
     bÄĻdzie
    0.07
    æľĥ
    0.07
     intention
    0.07
    ensem
    0.07
     бÑĥдÑĥÑĤ
    0.07
    Activations Density 0.026%

    No Known Activations