© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 58915
    Prev
    Next
    INDEX
    Explanations

    .makedirs

    np_max-act · gemini-2.0-flash

    The neuron detects calls or patterns for creating directories (e.g. `os.makedirs`/`mkdir`) in code.

    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
     frosting
    -0.06
    sword
    -0.06
     Elias
    -0.06
     stesso
    -0.06
     summers
    -0.06
     blank
    -0.06
    oload
    -0.06
     Simmons
    -0.06
    之后
    -0.05
     enquiry
    -0.05
    POSITIVE LOGITS
    .makedirs
    0.09
    akedirs
    0.07
    铺
    0.07
     dependent
    0.07
    ника
    0.07
    _cliente
    0.06
     trách
    0.06
     GOOGLE
    0.06
    SED
    0.06
    uding
    0.06
    Activations Density 0.001%

    No Known Activations