© 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. 30299
    Prev
    Next
    INDEX
    Explanations

    items related to clothing and fabric

    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
    illez
    -0.08
    igue
    -0.06
    overy
    -0.06
    eniable
    -0.06
    \Framework
    -0.06
    ẳng
    -0.06
     grounds
    -0.06
     often
    -0.06
    lias
    -0.06
    hazi
    -0.06
    POSITIVE LOGITS
     Pearson
    0.07
     surprisingly
    0.07
    rei
    0.07
     ÙĨص
    0.06
    ych
    0.06
     armored
    0.06
    BU
    0.06
    nea
    0.06
    afx
    0.06
    ettel
    0.06
    Activations Density 0.048%

    No Known Activations