© 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. 126667
    Prev
    Next
    INDEX
    Explanations

    verbs and nouns related to negation and denial

    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
     Å
    -0.07
     Mori
    -0.07
     Pink
    -0.06
    MBProgressHUD
    -0.06
     mouth
    -0.06
    ŀ
    -0.06
    asso
    -0.06
     Sob
    -0.06
    ć
    -0.05
    ervas
    -0.05
    POSITIVE LOGITS
     пÑĢоÑĩ
    0.07
    виÑĩ
    0.07
    >:</
    0.07
    اÛĮاÙĨ
    0.07
    alet
    0.07
    .bb
    0.07
    iola
    0.07
    кÑĢеÑĤ
    0.07
     ÙĩÙħÛĮÙĨ
    0.07
    .walk
    0.06
    Activations Density 0.000%

    No Known Activations