© 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 (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 92038
    Prev
    Next
    INDEX
    Explanations

    {

    np_max-act · gemini-2.0-flash

    import statements and their associated module or library names.

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

    This neuron detects the names of items being imported (the identifiers listed inside the curly braces of import statements).

    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
     DIC
    -0.07
    ��
    -0.07
    IndexOf
    -0.06
    nahme
    -0.06
     preparing
    -0.06
    Sanders
    -0.06
     puppies
    -0.06
    オリ
    -0.06
    -labelledby
    -0.06
     sextreffen
    -0.06
    POSITIVE LOGITS
    special
    0.08
    (false
    0.07
    .entity
    0.07
    >j
    0.06
     rating
    0.06
     Wear
    0.06
     Carson
    0.06
     nev
    0.06
     absurd
    0.06
    Health
    0.06
    Activations Density 0.002%

    No Known Activations