© 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. 28328
    Prev
    Next
    INDEX
    Explanations

    question marks indicating inquiries or interrogative statements

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

    The token pattern "<<?>>" marks the end of a question, immediately followed by the answer or response to that question in a Q&A format.

    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
    ingle
    -0.07
    راÙģ
    -0.06
    ابد
    -0.06
    ãĥĭãĥĥãĤ¯
    -0.06
    inge
    -0.06
    Å¡ka
    -0.06
    çī§
    -0.06
     Getty
    -0.06
    ikon
    -0.06
    ters
    -0.06
    POSITIVE LOGITS
     answer
    0.07
    oplevel
    0.07
     answered
    0.07
    ÃĤ
    0.07
    âĶ¬
    0.06
    çŃĭ
    0.06
     Answer
    0.06
    edar
    0.06
    Å
    0.06
    awai
    0.06
    Activations Density 0.001%

    No Known Activations