© 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. 106183
    Prev
    Next
    INDEX
    Explanations

    references to fashion-related items and accessories

    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
    ska
    -0.08
    ÅĻik
    -0.08
    lys
    -0.08
    stag
    -0.07
    (er
    -0.07
    xin
    -0.07
    icrous
    -0.07
    ned
    -0.07
    nie
    -0.07
    erness
    -0.07
    POSITIVE LOGITS
     such
    0.08
     items
    0.08
    件
    0.07
    /add
    0.07
     pieces
    0.06
    ornado
    0.06
     accompanying
    0.06
    alette
    0.06
     accompany
    0.06
     accessory
    0.06
    Activations Density 0.005%

    No Known Activations