© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 56655
    Prev
    Next
    INDEX
    Explanations

    phrases expressing skepticism or critique towards authority and societal norms

    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
     
    -0.06
       
    -0.06
     role
    -0.06
     bias
    -0.06
     Wor
    -0.05
     background
    -0.05
     included
    -0.05
    ombs
    -0.05
     Jew
    -0.05
    Âł
    -0.05
    POSITIVE LOGITS
    rysler
    0.08
    tility
    0.08
     Incontri
    0.08
    íĨłíĨł
    0.08
    odash
    0.07
    asin
    0.07
    everything
    0.07
    ItemList
    0.07
    StackSize
    0.07
    á»ģ
    0.07
    Activations Density 0.016%

    No Known Activations