© 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. 124720
    Prev
    Next
    INDEX
    Explanations

    .makeText

    np_max-act · gemini-2.0-flash

    issues related to user input or interaction in Android applications.

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

    This neuron detects floating‐point numeric literals (i.e. numbers with decimal points) in the code.

    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
     Unters
    -0.07
     emojis
    -0.07
     SPL
    -0.07
    ​
    -0.06
    _Ad
    -0.06
    ζί
    -0.06
    环
    -0.06
     toddlers
    -0.06
    ている
    -0.06
    _st
    -0.06
    POSITIVE LOGITS
    .makeText
    0.13
     Skin
    0.07
    /pre
    0.07
     Genesis
    0.07
     Machinery
    0.07
    ่สามารถ
    0.06
    spirit
    0.06
    금
    0.06
    谋
    0.06
    Direction
    0.06
    Activations Density 0.000%

    No Known Activations