© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 38002
    Prev
    Next
    INDEX
    Explanations

    p

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on isolated “p” or “P” tokens—typically single‐letter model/suffix identifiers in product names (e.g. “6P” or “6p”).

    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
     एव
    -0.07
    VICES
    -0.07
     nowrap
    -0.06
     цю
    -0.06
    GridView
    -0.06
     Processor
    -0.06
    xima
    -0.06
     Equals
    -0.06
     sulfate
    -0.06
    xEA
    -0.06
    POSITIVE LOGITS
    طب
    0.07
     Validator
    0.06
    olg
    0.06
    oling
    0.06
    开展
    0.06
    úp
    0.06
     dwelling
    0.06
     displ
    0.06
    λεί
    0.06
     上涨
    0.06
    Activations Density 0.000%

    No Known Activations