© 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. 128351
    Prev
    Next
    INDEX
    Explanations

    programming inheritance and types

    np_max-act · gemini-2.0-flash

    This neuron fires on substrings and tokens related to “polymorphic,” i.e. references to polymorphic model associations.

    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
    ası
    -0.08
     lái
    -0.07
    LG
    -0.06
    _FALSE
    -0.06
    sector
    -0.06
     heroine
    -0.06
    ılıp
    -0.06
    _COLS
    -0.06
    _$_
    -0.06
     Premi
    -0.06
    POSITIVE LOGITS
     deploying
    0.06
     něco
    0.06
    reachable
    0.06
     Literal
    0.06
    鹿
    0.06
    .sqlite
    0.06
     متحده
    0.06
     немного
    0.06
     Ž
    0.06
    剑
    0.06
    Activations Density 0.005%

    No Known Activations