© 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. 4455
    Prev
    Next
    INDEX
    Explanations

    phrases warning against potential dangers or harmful outcomes

    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
    allel
    -0.08
    ober
    -0.08
    ews
    -0.07
    agger
    -0.06
    ptime
    -0.06
    eel
    -0.06
     ÙĪاÙĤع
    -0.06
    à¸ģ
    -0.05
    ucas
    -0.05
    Äįan
    -0.05
    POSITIVE LOGITS
     dangers
    0.14
     danger
    0.11
     Danger
    0.11
    eware
    0.09
    danger
    0.08
     dangerous
    0.08
    -danger
    0.08
     à¤ĸतर
    0.07
     dangerously
    0.07
     risks
    0.07
    Activations Density 0.010%

    No Known Activations