© 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. 17-LLAMASCOPE-RES-131K
    11. 83465
    Prev
    Next
    INDEX
    Explanations

    mentions of financial support and funding in research contexts

    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
    eneg
    -0.07
    udeau
    -0.07
    owitz
    -0.06
    ifax
    -0.06
    mans
    -0.05
    uario
    -0.05
    lech
    -0.05
    owi
    -0.05
    ross
    -0.05
    achten
    -0.05
    POSITIVE LOGITS
    support
    0.08
    æĿ¥èĩª
    0.07
    æĿ¥äºĨ
    0.07
    /support
    0.07
    agli
    0.07
    iert
    0.07
    RIPT
    0.06
     Partial
    0.06
     support
    0.06
    ponsor
    0.06
    Activations Density 0.019%

    No Known Activations