© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 90644
    Prev
    Next
    INDEX
    Explanations

    code, configurations, logs

    np_max-act · gemini-2.0-flash

    The neuron activates on Python code tokens—especially module and function names like “subprocess,” “python,” and other identifiers—i.e. it detects Python code elements.

    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
    -legged
    -0.07
    -message
    -0.07
    नल
    -0.06
     chicks
    -0.06
     जनत
    -0.06
     occurred
    -0.06
    .setBackgroundColor
    -0.06
     orthodox
    -0.06
    ِر
    -0.06
     Zá
    -0.06
    POSITIVE LOGITS
     rezerv
    0.07
    stay
    0.07
    ˆ
    0.07
    '])->
    0.06
     qint
    0.06
     saç
    0.06
    pkt
    0.06
     combust
    0.06
    _nama
    0.06
    clidean
    0.06
    Activations Density 0.026%

    No Known Activations