© 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 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. 85764
    Prev
    Next
    INDEX
    Explanations

    technical jargon and tools related to home improvement and flooring

    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
    ä¹ĭ
    -0.08
    »
    -0.07
    èĢħçļĦ
    -0.07
    ģ
    -0.07
    3
    -0.07
    å·ŀ
    -0.06
    à¥į
    -0.06
     ä¹ĭ
    -0.06
    į¼
    -0.06
    orge
    -0.06
    POSITIVE LOGITS
    µ¬
    0.07
    riere
    0.07
    .sponge
    0.07
    ¬
    0.07
    emens
    0.07
    ocol
    0.07
    ò
    0.06
     jose
    0.06
    escort
    0.06
    dux
    0.06
    Activations Density 0.096%

    No Known Activations