© 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. 118713
    Prev
    Next
    INDEX
    Explanations

    various types of furniture, particularly tables and their styles

    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
     Lawn
    -0.07
    ertest
    -0.06
    alamat
    -0.06
    /php
    -0.06
    rega
    -0.06
     Jacket
    -0.06
     Couch
    -0.06
    uti
    -0.06
    lds
    -0.06
    мÑı
    -0.06
    POSITIVE LOGITS
     bay
    0.07
     Living
    0.07
     Murphy
    0.06
     Claw
    0.06
     living
    0.06
     ideas
    0.06
     Salv
    0.06
     contemporary
    0.06
    issing
    0.06
    .alibaba
    0.06
    Activations Density 0.136%

    No Known Activations