© 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. 6537
    Prev
    Next
    INDEX
    Explanations

    ICD codes

    np_max-act · gemini-2.0-flash

    medical record identifiers and associated data.

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

    The neuron fires on number tokens that appear as the decimal—or second—part of medical diagnosis codes (e.g. the “.9” or “.02” in ICD‐style codes).

    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
     Cleans
    -0.06
    _navigation
    -0.06
    component
    -0.06
    choice
    -0.06
    :param
    -0.06
    Nd
    -0.06
    'B
    -0.06
    ”
    -0.06
    ظة
    -0.06
     Recently
    -0.06
    POSITIVE LOGITS
     普通
    0.07
     Ethereum
    0.07
    ��
    0.07
     ${
    0.07
    �
    0.06
    ايش
    0.06
    ">${
    0.06
    /rc
    0.06
    지노
    0.06
     vài
    0.06
    Activations Density 0.001%

    No Known Activations