© 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. 56856
    Prev
    Next
    INDEX
    Explanations

    information related to recycling clothing and sustainable fashion practices

    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
    cek
    -0.07
     rabbits
    -0.06
    ceso
    -0.06
    987
    -0.06
     alter
    -0.06
    798
    -0.06
    ptest
    -0.06
    .Shared
    -0.06
    SWG
    -0.05
     pump
    -0.05
    POSITIVE LOGITS
     collection
    0.09
     Collection
    0.09
    submitButton
    0.09
     collecting
    0.08
     collect
    0.08
    -collection
    0.08
     Collect
    0.08
     collected
    0.08
    ossed
    0.07
    .collect
    0.07
    Activations Density 0.010%

    No Known Activations