© 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. 55654
    Prev
    Next
    INDEX
    Explanations

    gerunds and their usage 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
     once
    -0.07
    Łèĥ½
    -0.06
    athe
    -0.06
     first
    -0.06
    ivan
    -0.06
    ácil
    -0.06
    ect
    -0.06
    eren
    -0.06
    maal
    -0.06
     ساÙĦÙħ
    -0.06
    POSITIVE LOGITS
     since
    0.19
     lately
    0.19
    since
    0.17
    以æĿ¥
    0.14
     Since
    0.13
    Since
    0.13
     ÙħÙĨØ°
    0.13
    _since
    0.13
     depuis
    0.12
     seit
    0.12
    Activations Density 0.040%

    No Known Activations