© 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. 129416
    Prev
    Next
    INDEX
    Explanations

    the name "Stewart" in various 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
    Occurred
    -0.09
    ëģĶ
    -0.08
    .infinity
    -0.08
    æ³³
    -0.08
    ModelProperty
    -0.08
    ural
    -0.07
    éru
    -0.07
    uta
    -0.07
    erals
    -0.07
    aban
    -0.07
    POSITIVE LOGITS
    sville
    0.09
    ize
    0.07
    ellar
    0.07
    ish
    0.07
     YaÅŁ
    0.06
    ign
    0.06
    reck
    0.06
    lights
    0.06
    ator
    0.06
    769
    0.06
    Activations Density 0.010%

    No Known Activations