© 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. 4235
    Prev
    Next
    INDEX
    Explanations

    expressions of uncertainty and confusion in understanding situations or narratives

    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
     perfect
    -0.07
    adar
    -0.06
     unlikely
    -0.06
    deo
    -0.06
     slice
    -0.06
     paced
    -0.06
    ease
    -0.06
     Perfect
    -0.05
    slice
    -0.05
     att
    -0.05
    POSITIVE LOGITS
     anymore
    0.09
     exactly
    0.08
    åĪ°åºķ
    0.08
    actly
    0.08
     vlastnÄĽ
    0.08
    ή
    0.07
    .BorderFactory
    0.07
    ouis
    0.07
     EITHER
    0.07
    Purpose
    0.07
    Activations Density 0.032%

    No Known Activations