© 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. 89191
    Prev
    Next
    INDEX
    Explanations

    Emphasis, comparison, surprise

    np_max-act · gemini-2.0-flash

    The neuron fires on numeric tokens representing decimal or floating‐point values.

    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
     í
    -0.07
    	attack
    -0.07
    識
    -0.06
     dramas
    -0.06
     cour
    -0.06
    replacement
    -0.06
     tier
    -0.06
    dead
    -0.06
     peppers
    -0.06
    िछल
    -0.06
    POSITIVE LOGITS
     노래
    0.06
     sağlamak
    0.06
    +xml
    0.06
    Scala
    0.06
    _visited
    0.06
    VERTISE
    0.06
     Hund
    0.06
    _package
    0.06
    че
    0.06
    =http
    0.06
    Activations Density 0.071%

    No Known Activations