© 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. 15-LLAMASCOPE-RES-131K
    11. 26366
    Prev
    Next
    INDEX
    Explanations

    mentions of physical appearance and skin-related issues

    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
    iffs
    -0.08
    ient
    -0.08
    [op
    -0.07
    unday
    -0.07
     âĹĦ
    -0.07
    à¤¾à¤ľà¤ª
    -0.07
    ushima
    -0.07
     Rencontre
    -0.07
    ÑĩÑı
    -0.07
    ÏĩεδÏĮν
    -0.07
    POSITIVE LOGITS
    ICENSE
    0.06
     my
    0.06
    obus
    0.06
     PIL
    0.06
     Pand
    0.06
    IDES
    0.06
     blaze
    0.06
     TextAlign
    0.05
    sei
    0.05
     pil
    0.05
    Activations Density 0.005%

    No Known Activations