© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 83583
    Prev
    Next
    INDEX
    Explanations

    arguments and sentiments related to skepticism and critique of established beliefs or theories

    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
    poÄįet
    -0.07
    PropertyName
    -0.07
    antino
    -0.07
    ongyang
    -0.07
    idot
    -0.07
    oba
    -0.07
    CLR
    -0.07
    pras
    -0.07
    ocode
    -0.07
    leme
    -0.07
    POSITIVE LOGITS
     myself
    0.15
     my
    0.12
    æĪij
    0.10
    æĪijçļĦ
    0.09
     saya
    0.09
    ï¼ĮæĪij
    0.09
     personally
    0.09
     I
    0.08
     minha
    0.08
     meiner
    0.08
    Activations Density 0.080%

    No Known Activations