© 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. 118745
    Prev
    Next
    INDEX
    Explanations

    the term "notwithstanding" and its variants, indicating exceptions or conditions despite other factors

    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
    bedo
    -0.07
    ustr
    -0.06
    Ľi
    -0.06
    isation
    -0.06
    nc
    -0.06
    orce
    -0.06
    inition
    -0.06
    .getChildAt
    -0.06
    opis
    -0.06
    bers
    -0.06
    POSITIVE LOGITS
    theless
    0.07
     how
    0.07
    oulos
    0.07
    etheless
    0.07
    t
    0.07
     recent
    0.07
    ÛĮ
    0.07
    acre
    0.06
    aal
    0.06
    withstanding
    0.06
    Activations Density 0.002%

    No Known Activations