© 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. 56241
    Prev
    Next
    INDEX
    Explanations

    cosmetic and beauty-related products and terminology

    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
    @student
    -0.07
    ÑĢап
    -0.07
     Wort
    -0.07
    htub
    -0.07
    prech
    -0.07
    istrovstvÃŃ
    -0.06
    lue
    -0.06
    AGR
    -0.06
    ovice
    -0.06
    iar
    -0.06
    POSITIVE LOGITS
     Sep
    0.09
    akeup
    0.09
     makeup
    0.07
     pig
    0.07
     drug
    0.07
     Makeup
    0.06
    077
    0.06
     eyel
    0.06
    drug
    0.06
     cruelty
    0.06
    Activations Density 0.004%

    No Known Activations