© 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. 5839
    Prev
    Next
    INDEX
    Explanations

    supply

    np_max-act · gemini-2.0-flash

    This neuron activates on numerical and quantitative terms—especially figures and supply‐related numbers (e.g. total, supply, million, bitcoins).

    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
     own
    -0.07
     ord
    -0.06
     Twelve
    -0.06
    .fontSize
    -0.06
     먼저
    -0.06
    金融
    -0.06
    ESPN
    -0.06
    urface
    -0.06
     dock
    -0.06
     �
    -0.06
    POSITIVE LOGITS
    ActionTypes
    0.07
    рот
    0.07
    Third
    0.07
    और
    0.07
     ISA
    0.07
     말씀
    0.06
    	TRACE
    0.06
     &&↵
    0.06
     总
    0.06
    plusplus
    0.06
    Activations Density 0.005%

    No Known Activations