© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 41493
    Prev
    Next
    INDEX
    Explanations

    keywords related to programming errors and exceptions

    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
    anger
    -0.07
    exion
    -0.07
    exus
    -0.07
    chten
    -0.07
    engin
    -0.06
    odo
    -0.06
    iams
    -0.06
    eu
    -0.06
    олÑĮ
    -0.06
    physical
    -0.06
    POSITIVE LOGITS
    .Parcel
    0.07
     Mist
    0.07
    Ģ
    0.07
    classCallCheck
    0.06
    ONTAL
    0.06
    akest
    0.06
    373
    0.06
    azı
    0.06
    aný
    0.06
    indo
    0.06
    Activations Density 0.000%

    No Known Activations