© 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. 27618
    Prev
    Next
    INDEX
    Explanations

    queries and discussions about timing and uncertainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Interrogative elements including question marks and associated words that form questions or express uncertainty.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    zech
    -0.07
    uni
    -0.07
    cÃŃm
    -0.06
    EEK
    -0.06
    uzzi
    -0.06
    rán
    -0.06
    .EN
    -0.06
     mø
    -0.06
    umbs
    -0.06
    UNS
    -0.06
    POSITIVE LOGITS
     ìĸ¸ìłľ
    0.07
    MainThread
    0.07
     sooner
    0.07
    ibre
    0.06
     Immediate
    0.06
    umin
    0.06
     whenever
    0.06
    ãģ£ãģ¨
    0.06
     immediate
    0.06
    .scalablytyped
    0.06
    Activations Density 0.054%

    No Known Activations