© 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. 9516
    Prev
    Next
    INDEX
    Explanations

    user input code

    np_max-act · gemini-2.0-flash

    This neuron detects Java code for reading user input (e.g. Scanner instantiation and its nextX() calls).

    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
    Signal
    -0.07
    _redirect
    -0.07
    (article
    -0.07
     predictable
    -0.07
     collectors
    -0.07
     Massive
    -0.07
    Valid
    -0.07
     Driver
    -0.06
     flight
    -0.06
     theater
    -0.06
    POSITIVE LOGITS
     mrb
    0.07
    leetcode
    0.06
    255
    0.06
     (...)
    0.06
     باز
    0.06
    .cbo
    0.05
     Ев
    0.05
    .PropertyType
    0.05
     hrom
    0.05
    トル
    0.05
    Activations Density 0.002%

    No Known Activations