© 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. 88072
    Prev
    Next
    INDEX
    Explanations

    statements expressing skepticism about common beliefs or assumptions

    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
    loat
    -0.07
    usch
    -0.06
    ë³
    -0.06
    ona
    -0.06
    ington
    -0.06
    universal
    -0.06
    ër
    -0.06
    ukt
    -0.06
    nia
    -0.06
     IIC
    -0.06
    POSITIVE LOGITS
     Transparency
    0.12
     transparency
    0.12
     transparent
    0.09
     Transparent
    0.09
    transparent
    0.08
    Transparent
    0.08
    æ¸ħæ¥ļ
    0.08
     accountability
    0.07
    -transparent
    0.07
     Accountability
    0.07
    Activations Density 0.060%

    No Known Activations