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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 57147
    Prev
    Next
    INDEX
    Explanations

    words 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
    æ£
    -0.07
    lander
    -0.07
    .configuration
    -0.06
    лÑĥг
    -0.06
    yg
    -0.06
     trading
    -0.06
    á»ķi
    -0.06
     cez
    -0.06
    lid
    -0.06
    ÑĥÑĢа
    -0.06
    POSITIVE LOGITS
    ìĭĿ
    0.07
    íıī
    0.07
    Å¡ak
    0.06
     dere
    0.06
    å¼ı
    0.06
    istrovstvÃŃ
    0.06
    ToLeft
    0.06
    íķŃ
    0.06
    akeup
    0.06
     Fa
    0.06
    Activations Density 0.055%

    No Known Activations