© 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. 58286
    Prev
    Next
    INDEX
    Explanations

    discretionary

    np_max-act · gemini-2.0-flash

    The main thing this neuron does is detect legal terminology referring to government law‐enforcement actors and the FTCA’s discretionary‐function/immunity exemption.

    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
     الرم
    -0.06
     subclass
    -0.06
    орту
    -0.06
     fuels
    -0.06
     LLC
    -0.06
     inmate
    -0.06
    决定
    -0.06
    610
    -0.06
     آثار
    -0.06
    orney
    -0.06
    POSITIVE LOGITS
    (X
    0.07
    lier
    0.07
    Hom
    0.07
    _CUDA
    0.06
    (div
    0.06
    			↵			↵
    0.06
    (A
    0.06
     स
    0.06
     px
    0.06
    ('(
    0.06
    Activations Density 0.010%

    No Known Activations