© 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. 70120
    Prev
    Next
    INDEX
    Explanations

    referenced proper nouns, particularly names and organizations

    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
     nouve
    -0.07
    ãĥIJãĤ¤
    -0.07
    âĢİ
    -0.07
     vô
    -0.07
     dziew
    -0.07
     zdrav
    -0.07
    emez
    -0.07
     éĹ
    -0.07
    ứt
    -0.07
     [|
    -0.06
    POSITIVE LOGITS
     itself
    0.07
    _HERSHEY
    0.07
    åģ¥
    0.07
    astically
    0.06
    erto
    0.06
    ÑĢоваÑĤÑĮ
    0.06
    æ°ı
    0.06
    åģ
    0.06
    !(
    0.06
    inski
    0.06
    Activations Density 0.037%

    No Known Activations