© 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. 41472
    Prev
    Next
    INDEX
    Explanations

    codes and numbers

    np_max-act · gemini-2.0-flash

    This neuron detects ICD-style medical diagnosis codes (letter–digit patterns like “J06.9”) and their accompanying descriptions.

    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
    Redux
    -0.07
    (Task
    -0.07
     deutschland
    -0.06
     herramient
    -0.06
    روع
    -0.06
    ladu
    -0.06
    _complex
    -0.06
     поб
    -0.06
    RenderWindow
    -0.06
    _POINTER
    -0.06
    POSITIVE LOGITS
     ax
    0.07
     Benjamin
    0.06
    Scaler
    0.06
     Lak
    0.06
     invention
    0.06
    -points
    0.06
     strategist
    0.06
    colm
    0.06
    池
    0.06
     предел
    0.06
    Activations Density 0.004%

    No Known Activations