© 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. 93934
    Prev
    Next
    INDEX
    Explanations

    expressions related to disabling or turning off features and warnings in code

    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
    iffies
    -0.07
    ondon
    -0.07
    bet
    -0.07
    emean
    -0.07
    pector
    -0.06
    graf
    -0.06
     tu
    -0.06
     COUR
    -0.06
    bolt
    -0.06
     QTest
    -0.06
    POSITIVE LOGITS
     automatic
    0.10
     altogether
    0.10
    -automatic
    0.08
     unwanted
    0.08
     Automatic
    0.08
    automatic
    0.08
    ĴĮ
    0.08
    æİī
    0.07
     undes
    0.07
     automát
    0.07
    Activations Density 0.023%

    No Known Activations