© 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. 74913
    Prev
    Next
    INDEX
    Explanations

    blended learning

    np_max-act · gemini-2.0-flash

    phrases related to cloud computing and infrastructure solutions.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron detects terms that denote mixed or combined models—e.g. “hybrid,” “blended,” (as in hybrid cloud or blended learning).

    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
    	layer
    -0.07
     티
    -0.07
    -sdk
    -0.07
     deleted
    -0.06
     extremist
    -0.06
    -west
    -0.06
     sıkıntı
    -0.06
     Taylor
    -0.06
    偷
    -0.06
     انسان
    -0.06
    POSITIVE LOGITS
    -period
    0.06
    容
    0.06
    -parts
    0.06
     DELETE
    0.06
    igit
    0.06
    alto
    0.06
    "]=>
    0.06
    ư�
    0.06
    举
    0.06
     ];
    0.06
    Activations Density 0.011%

    No Known Activations