© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 128819
    Prev
    Next
    INDEX
    Explanations

    expressions of surprise or acknowledgment

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

    Brief exclamatory expressions that signal emotional reactions or sudden realizations, typically occurring at the beginning of a response or statement.

    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
    Ðĭ
    -0.07
    rant
    -0.06
     Do
    -0.06
    istica
    -0.06
    ologia
    -0.06
    .BL
    -0.06
     mee
    -0.06
    кÑĤа
    -0.06
     PDO
    -0.06
    ught
    -0.06
    POSITIVE LOGITS
    mui
    0.07
    amiliar
    0.07
     Ingen
    0.07
    åİŁæĿ¥
    0.06
     interes
    0.06
    orman
    0.06
    ries
    0.06
    bara
    0.06
    ystery
    0.06
    ingo
    0.06
    Activations Density 0.023%

    No Known Activations