© 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. 15-LLAMASCOPE-RES-131K
    11. 88159
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing clarity and the need for precise communication

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

    Phrases that signal clarification, emphasis, or prevention of misunderstanding in communication.

    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
    omor
    -0.06
    ewis
    -0.06
     Revel
    -0.06
    ULAR
    -0.06
     Bilder
    -0.06
    erg
    -0.05
     insol
    -0.05
     Bloc
    -0.05
    rimon
    -0.05
    jong
    -0.05
    POSITIVE LOGITS
     clarify
    0.09
     clarification
    0.09
     misunderstanding
    0.08
     misconception
    0.08
     misunderstood
    0.08
     confusion
    0.08
     clarified
    0.08
     clear
    0.07
     disclaimer
    0.07
     clears
    0.07
    Activations Density 0.102%

    No Known Activations