© 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. 901
    Prev
    Next
    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash

    Python code implementations for numerical methods and mathematical algorithms, specifically related to solving differential equations.

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

    The neuron activates on words referring to writing or implementing code (e.g., coding, implement, MatLab), so it’s detecting programming/code-related terms.

    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
     Chapman
    -0.07
     datap
    -0.07
    otre
    -0.07
    摘
    -0.06
    .Drawable
    -0.06
     Mun
    -0.06
     masks
    -0.06
    datap
    -0.06
    050
    -0.06
     queer
    -0.06
    POSITIVE LOGITS
    opyright
    0.06
    usunda
    0.06
     تلف
    0.06
     getItemCount
    0.06
     машин
    0.06
    (nd
    0.06
     instituted
    0.06
     cenu
    0.06
     команд
    0.06
    quota
    0.06
    Activations Density 0.106%

    No Known Activations