© 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. 15-LLAMASCOPE-RES-131K
    11. 27657
    Prev
    Next
    INDEX
    Explanations

    references to software packages or modules

    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
    erton
    -0.07
    upo
    -0.07
    yg
    -0.07
    enia
    -0.07
    .googlecode
    -0.06
    inja
    -0.06
    rvé
    -0.06
    YG
    -0.06
    ras
    -0.06
    ë°ĺ
    -0.06
    POSITIVE LOGITS
    chg
    0.07
    wand
    0.07
    .contents
    0.06
    ä»
    0.06
    707
    0.06
    zione
    0.06
    WillAppear
    0.06
    ÙĪÛĮد
    0.06
     обÑıз
    0.06
     ÑģобоÑİ
    0.06
    Activations Density 0.001%

    No Known Activations