© 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. 15-LLAMASCOPE-RES-131K
    11. 26524
    Prev
    Next
    INDEX
    Explanations

    references to authority figures or expert opinions

    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
    è¾ŀ
    -0.07
    ymm
    -0.07
    CDF
    -0.07
    ensation
    -0.07
    ertas
    -0.07
    @@
    -0.06
    æ®Ĭ
    -0.06
     tá»
    -0.06
    aÄŁ
    -0.06
    stru
    -0.06
    POSITIVE LOGITS
     Aires
    0.06
     Nil
    0.06
     mak
    0.06
    ени
    0.06
     think
    0.05
     performed
    0.05
     meta
    0.05
     independent
    0.05
    arr
    0.05
    aign
    0.05
    Activations Density 0.016%

    No Known Activations