© 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. 79134
    Prev
    Next
    INDEX
    Explanations

    phrases related to misinformation and skepticism surrounding science and public policy

    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
     Patrol
    -0.07
     parten
    -0.07
    aina
    -0.07
    Ư
    -0.07
    ë¶Ī
    -0.06
    ếp
    -0.06
    nelly
    -0.06
     succesfully
    -0.06
     Wert
    -0.06
     naw
    -0.06
    POSITIVE LOGITS
     Pub
    0.07
     mass
    0.06
     vi
    0.06
     Covid
    0.06
     scientific
    0.06
     deaths
    0.06
     worldwide
    0.06
    iram
    0.05
    jin
    0.05
    (Call
    0.05
    Activations Density 0.003%

    No Known Activations