© 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. 79023
    Prev
    Next
    INDEX
    Explanations

    terms related to microwave radiation and its biological effects

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

    Portions of website URLs, document references, or bibliographic citations, particularly file paths, publication titles, author names, and institutional affiliations that form part of digital resource identifiers or formal citations.

    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
    âĢ¦↵
    -0.15
    âĢ¦”
    -0.11
    Âłin
    -0.11
     âĢ¦↵
    -0.10
    âĢ¦I
    -0.09
    âĢ¦
    -0.09
    ..↵
    -0.09
    _HERSHEY
    -0.09
     [âĢ¦]↵
    -0.08
    âĢ¦.
    -0.08
    POSITIVE LOGITS
    #ac
    0.13
    _________________↵↵
    0.13
     nues
    0.13
    .getElements
    0.13
     -*-č↵
    0.12
    ìŀIJìĿ¸
    0.12
    .Reporting
    0.12
    #__
    0.12
     ì¡
    0.12
     знов
    0.12
    Activations Density 5.835%

    No Known Activations