© 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. 124918
    Prev
    Next
    INDEX
    Explanations

    Programming languages

    np_max-act · gemini-2.0-flash

    This neuron fires on names of programming languages, libraries, and related frameworks (e.g. “Java,” “LWJGL,” “Python,” “Cython”).

    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
    _on
    -0.07
     VLC
    -0.07
    _short
    -0.07
    ’den
    -0.07
    _config
    -0.07
    .general
    -0.07
     Kho
    -0.06
     defects
    -0.06
    .RIGHT
    -0.06
     sigma
    -0.06
    POSITIVE LOGITS
     dur
    0.06
     sme
    0.06
     مواطنة
    0.06
    ALER
    0.06
    (bg
    0.05
     καθ
    0.05
    Fld
    0.05
     glGet
    0.05
     GUIDE
    0.05
    RAFT
    0.05
    Activations Density 0.029%

    No Known Activations