Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 91034
    Prev
    Next
    INDEX
    Explanations

    import

    np_max-act · gemini-2.0-flash

    commands related to library installation in Python.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron responds to Python code snippets—especially lines that begin with the `import` keyword or the `python` code‐block marker.

    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
    Alt
    -0.07
    _modules
    -0.07
    CHIP
    -0.07
    interaction
    -0.06
    Chip
    -0.06
    meaning
    -0.06
     Clay
    -0.06
    _mean
    -0.06
    .he
    -0.06
    جی
    -0.06
    POSITIVE LOGITS
    secured
    0.07
     rendez
    0.06
    ㅎ
    0.06
     Pee
    0.06
    pcodes
    0.06
    ไซ
    0.06
     ま
    0.06
     para
    0.06
    ABILITY
    0.06
     Dh
    0.06
    Activations Density 0.019%

    No Known Activations