© 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. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 89407
    Prev
    Next
    INDEX
    Explanations

    causation

    np_max-act · gemini-2.0-flash

    This neuron detects causal and speculative signal words—verbs and modals like “cause,” “leads,” “may,” “likely,” and “triggers” that express causation or possibility.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Unsigned
    -0.07
    Agent
    -0.07
     Pract
    -0.07
     Murdoch
    -0.06
    ＾
    -0.06
     Star
    -0.06
    птом
    -0.06
    ุข
    -0.06
    .dst
    -0.06
     gösteren
    -0.06
    POSITIVE LOGITS
     linha
    0.07
    rebbe
    0.07
    -calendar
    0.07
    .assertEqual
    0.06
    (history
    0.06
    ())
↵
↵
    0.06
            
↵        
↵
    0.06
    ΑΜ
    0.06
    レイ
    0.06
     ↵        ↵
    0.06
    Activations Density 0.066%

    No Known Activations