© 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. 44626
    Prev
    Next
    INDEX
    Explanations

    ==

    np_max-act · gemini-2.0-flash

    The neuron activates on MSBuild XML Condition attributes and their comparison expressions (e.g. "'$(Configuration)' == 'Debug'").

    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
    it
    -0.06
    -ves
    -0.06
    (require
    -0.06
     Dum
    -0.06
     patents
    -0.06
    Dup
    -0.06
    	tag
    -0.06
     Пло
    -0.06
    748
    -0.06
    もしれない
    -0.06
    POSITIVE LOGITS
     jsonify
    0.07
     LDL
    0.06
    (mid
    0.06
     prayed
    0.06
     PX
    0.06
    ucked
    0.06
    YSIS
    0.06
     실행
    0.06
    增
    0.06
     Fiona
    0.06
    Activations Density 0.001%

    No Known Activations