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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 58364
    Prev
    Next
    INDEX
    Explanations

    conjunctions and coordinating phrases in contexts discussing medical or clinical topics

    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
    staw
    -0.07
     Decompiled
    -0.07
    ekli
    -0.07
    idden
    -0.06
    :///
    -0.06
    oÅĻ
    -0.06
    ased
    -0.06
    .Apis
    -0.06
    ://
    -0.06
    éŀ
    -0.06
    POSITIVE LOGITS
     even
    0.11
    çĶļèĩ³
    0.09
    even
    0.09
     даже
    0.09
     sogar
    0.08
     beyond
    0.08
     навÑĸÑĤÑĮ
    0.08
     higher
    0.07
     même
    0.07
     hatta
    0.07
    Activations Density 0.028%

    No Known Activations