© 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. 41408
    Prev
    Next
    INDEX
    Explanations

    exceptions

    np_max-act · gemini-2.0-flash

    The neuron fires on text describing software distribution details—e.g. version names and which packages or builds are provided or available.

    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
    COMMAND
    -0.07
    eygamber
    -0.07
     exercises
    -0.06
    _stderr
    -0.06
    ."""↵↵
    -0.06
    paralleled
    -0.06
    peated
    -0.06
    _bug
    -0.06
    devices
    -0.06
     Dak
    -0.06
    POSITIVE LOGITS
    施工
    0.08
     国家
    0.07
    .organ
    0.06
    ..
    0.06
     Tập
    0.06
    /.↵
    0.06
    مام
    0.06
     вод
    0.06
     الشي
    0.06
     mutable
    0.06
    Activations Density 0.035%

    No Known Activations