© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 1332
    Prev
    Next
    INDEX
    Explanations

    words related to the Gradle build system and its operations

    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
    ülü
    -0.06
    tür
    -0.06
    rud
    -0.06
    throp
    -0.06
    ÃľM
    -0.06
    laden
    -0.06
    年代
    -0.06
    ických
    -0.06
    Mgr
    -0.06
    lü
    -0.06
    POSITIVE LOGITS
    indle
    0.07
    -compatible
    0.07
    -Compatible
    0.06
    usb
    0.06
    _Api
    0.06
    _WARN
    0.06
    _GP
    0.06
     Daw
    0.06
     sum
    0.06
    GPS
    0.06
    Activations Density 0.002%

    No Known Activations