© 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
    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. 90926
    Prev
    Next
    INDEX
    Explanations

    _APPRO

    np_max-act · gemini-2.0-flash

    This neuron activates on OpenCV API tokens, especially function names and constants from the cv2 library.

    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
    Td
    -0.07
     собою
    -0.07
    anio
    -0.07
    datas
    -0.07
     Lamar
    -0.07
    düğ
    -0.06
    =admin
    -0.06
    culate
    -0.06
     mutate
    -0.06
    (pDX
    -0.06
    POSITIVE LOGITS
    _APPRO
    0.11
     encourage
    0.07
     legitimacy
    0.07
     अप
    0.07
     nghiên
    0.07
     stationed
    0.07
     hardware
    0.06
     scholarships
    0.06
     exercitation
    0.06
     tighten
    0.06
    Activations Density 0.000%

    No Known Activations