© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 74171
    Prev
    Next
    INDEX
    Explanations

    pathway

    np_max-act · gemini-2.0-flash

    The neuron fires on mentions of specific molecular signaling pathways (e.g. PI3K/Akt/mTOR, Wnt/β-catenin, BMP signaling).

    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
    uke
    -0.07
    ong
    -0.07
    in
    -0.07
    的心
    -0.06
    /png
    -0.06
    аний
    -0.06
    antry
    -0.06
    amaha
    -0.06
     Ronaldo
    -0.06
    iyon
    -0.06
    POSITIVE LOGITS
    ='./
    0.06
    วล
    0.06
     emergence
    0.06
     assay
    0.06
     millennium
    0.06
    Checkout
    0.06
     Transform
    0.06
    	Dictionary
    0.06
     supra
    0.06
     JVM
    0.06
    Activations Density 0.010%

    No Known Activations