© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 15-LLAMASCOPE-RES-131K
    11. 1208
    Prev
    Next
    INDEX
    Explanations

    references to specific attributes or categories related to Irish film and other specific content types

    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
    ymm
    -0.07
     erotische
    -0.07
    CCI
    -0.07
    raci
    -0.07
    TRACE
    -0.06
     hlavy
    -0.06
    اÙĩÛĮ
    -0.06
     geil
    -0.06
    еко
    -0.06
    uno
    -0.06
    POSITIVE LOGITS
    inde
    0.07
    adia
    0.07
     Hann
    0.06
    refs
    0.06
    &q
    0.06
    str
    0.06
    strain
    0.06
    artin
    0.06
     vou
    0.05
    .refs
    0.05
    Activations Density 0.064%

    No Known Activations