© 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. 60570
    Prev
    Next
    INDEX
    Explanations

    words related to deception or inadequacy in performance

    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
    åĪ°çļĦ
    -0.06
    assin
    -0.06
    fest
    -0.06
    åIJİçļĦ
    -0.06
    eware
    -0.06
    ÑĤаÑĢ
    -0.06
    atie
    -0.06
    itian
    -0.06
    atal
    -0.05
    adelphia
    -0.05
    POSITIVE LOGITS
    à¥įयम
    0.07
    ompiler
    0.07
     Janeiro
    0.07
    ularity
    0.06
    iability
    0.06
    alnız
    0.06
    Ñĥй
    0.06
    çī
    0.06
    .documentation
    0.06
     proverb
    0.06
    Activations Density 0.038%

    No Known Activations