© 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. 56459
    Prev
    Next
    INDEX
    Explanations

    cheese

    np_max-act · gemini-2.0-flash

    types of cheese and their characteristics.

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

    The neuron responds to occurrences of cheese-related terminology, especially the word “cheese” itself and descriptive cheese attributes like rinds or types.

    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
    PathParam
    -0.07
    look
    -0.06
     packageName
    -0.06
     巴
    -0.06
    includes
    -0.06
    thumb
    -0.05
    Knight
    -0.05
    	draw
    -0.05
    ervo
    -0.05
    ADE
    -0.05
    POSITIVE LOGITS
     hemos
    0.07
     accordion
    0.07
    idir
    0.07
     italian
    0.06
     JSONObject
    0.06
    人間
    0.06
     Elm
    0.06
     Oval
    0.06
    .AlertDialog
    0.06
     önceki
    0.06
    Activations Density 0.010%

    No Known Activations