© 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
    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. 129776
    Prev
    Next
    INDEX
    Explanations

    import

    np_max-act · gemini-2.0-flash

    The neuron activates on import statements (i.e. the “import” keyword and associated module imports).

    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
    eah
    -0.06
    _aspect
    -0.06
     klim
    -0.06
    ImagePath
    -0.06
    PWM
    -0.06
    ��
    -0.06
    ไปย
    -0.06
    _SLOT
    -0.06
    itti
    -0.06
    elocity
    -0.06
    POSITIVE LOGITS
    _CHILD
    0.07
    .bo
    0.07
     Explos
    0.07
    .Route
    0.06
    .car
    0.06
     typeId
    0.06
     selectedIndex
    0.06
    필
    0.06
     Toxic
    0.06
    rollback
    0.06
    Activations Density 0.006%

    No Known Activations