© 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 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. 17-LLAMASCOPE-RES-131K
    11. 76453
    Prev
    Next
    INDEX
    Explanations

    elements related to programming errors or 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
    usal
    -0.06
    otor
    -0.06
    icha
    -0.06
    ä¹
    -0.06
    azzi
    -0.06
    .EntityFramework
    -0.05
     coward
    -0.05
    oli
    -0.05
     variation
    -0.05
    cases
    -0.05
    POSITIVE LOGITS
     bund
    0.08
    .bundle
    0.07
     Haley
    0.07
     Bund
    0.07
     aday
    0.07
    AMA
    0.07
    ];//
    0.07
    ipa
    0.07
    917
    0.06
     '&'
    0.06
    Activations Density 0.001%

    No Known Activations