© 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. 1461
    Prev
    Next
    INDEX
    Explanations

    phrases indicating various aspects of performance or execution, particularly in contexts of success, adjustment, or effort

    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
    gu
    -0.06
    eln
    -0.06
     ness
    -0.06
    é¼
    -0.05
    eld
    -0.05
    anza
    -0.05
    ekli
    -0.05
    abase
    -0.05
    inci
    -0.05
    lenen
    -0.05
    POSITIVE LOGITS
    yna
    0.08
     maduras
    0.07
    :maj
    0.07
    ourg
    0.07
     ones
    0.07
     öyle
    0.07
    .Metro
    0.06
     thereof
    0.06
    idebar
    0.06
    ulers
    0.06
    Activations Density 0.064%

    No Known Activations