© 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. 15916
    Prev
    Next
    INDEX
    Explanations

    references to specific numeric data and ownership concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    StrictEqual
    -0.07
    --*/↵
    -0.07
     ëĭ¤ìļ´ë°Ľê¸°
    -0.07
    ActionCreators
    -0.07
    _exports
    -0.06
    ãĥĸãĥª
    -0.06
    uos
    -0.06
    //**↵
    -0.06
    ιβ
    -0.06
    strap
    -0.06
    POSITIVE LOGITS
    ideo
    0.07
    ppard
    0.07
     behavior
    0.06
    alie
    0.06
    ¤í
    0.06
    ianne
    0.06
    eree
    0.06
    á»į
    0.06
     tape
    0.06
    ohen
    0.06
    Activations Density 0.000%

    No Known Activations