© 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. 85700
    Prev
    Next
    INDEX
    Explanations

    installed

    np_max-act · gemini-2.0-flash

    The neuron activates on text describing Python installation or version‐checking commands (e.g. mentions of “installed,” “installation,” “python 3 --version,” or using `sys.version`), i.e. instructions for installing or verifying Python.

    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
    γμα
    -0.08
    _LOCK
    -0.06
     DOI
    -0.06
    Girl
    -0.06
    Csv
    -0.06
    Bush
    -0.06
     pile
    -0.06
    Py
    -0.06
    					   
    -0.06
     ENTRY
    -0.06
    POSITIVE LOGITS
    monthly
    0.06
     direccion
    0.06
     обрат
    0.06
     agar
    0.06
     DU
    0.06
     Institut
    0.06
    (lon
    0.06
     (),
    0.06
     ADDR
    0.06
     abst
    0.06
    Activations Density 0.011%

    No Known Activations