© 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. 104488
    Prev
    Next
    INDEX
    Explanations

    references to the market and market-related conditions or trends

    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
    ingly
    -0.06
    usto
    -0.06
    ми
    -0.06
     Reverse
    -0.06
    aware
    -0.06
     Newtown
    -0.06
    ίÏĥ
    -0.06
     saja
    -0.05
    	fflush
    -0.05
     and
    -0.05
    POSITIVE LOGITS
    lingen
    0.08
    Ä°T
    0.07
    λαν
    0.07
    oq
    0.07
    jourd
    0.07
    REET
    0.07
    ãĥĽãĥĨãĥ«
    0.07
    ocket
    0.07
    bery
    0.07
    BuilderInterface
    0.07
    Activations Density 0.007%

    No Known Activations