© 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. 83487
    Prev
    Next
    INDEX
    Explanations

    references to health concerns regarding children's safety

    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
    ucus
    -0.07
     congress
    -0.07
     Drain
    -0.06
    eya
    -0.06
    arus
    -0.06
    atron
    -0.06
    405
    -0.06
     prelim
    -0.06
    cx
    -0.06
    uchos
    -0.06
    POSITIVE LOGITS
     tooth
    0.10
     fluoride
    0.10
     dental
    0.08
    çīĻ
    0.08
     voksne
    0.07
     dentist
    0.07
     Dental
    0.07
    etooth
    0.07
     enamel
    0.07
     Tooth
    0.07
    Activations Density 0.003%

    No Known Activations