© 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. 118831
    Prev
    Next
    INDEX
    Explanations

    articles or determiners indicating singular nouns

    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
     zdrav
    -0.08
    HeaderCode
    -0.07
    IIIK
    -0.07
    (EXPR
    -0.07
    ->___
    -0.07
    ÃĸL
    -0.07
    IRROR
    -0.07
    dummy
    -0.07
    à¤Ĺढ
    -0.07
    errick
    -0.07
    POSITIVE LOGITS
    ugh
    0.07
    ãĥ©ãĥĥãĤ¯
    0.07
    UBL
    0.06
    IDI
    0.06
     vezes
    0.06
     set
    0.06
     Pir
    0.06
    acre
    0.06
    íķ´ìĦľ
    0.06
    UnitOfWork
    0.05
    Activations Density 0.007%

    No Known Activations