© 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. 58608
    Prev
    Next
    INDEX
    Explanations

    tests/testing

    np_max-act · gemini-2.0-flash

    This neuron detects words referring to trials or tests (e.g. “test,” “tests,” “challenge,” “ordeal”) in narrative 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
    微笑
    -0.07
     Lowell
    -0.07
     після
    -0.06
    肯
    -0.06
     пояс
    -0.06
     thải
    -0.06
     možná
    -0.06
     �
    -0.06
     coef
    -0.06
    Normalize
    -0.06
    POSITIVE LOGITS
     Test
    0.08
     test
    0.07
     tested
    0.07
     Controls
    0.07
     Tested
    0.06
     FITNESS
    0.06
    .modules
    0.06
    ylim
    0.06
     tests
    0.06
    -testing
    0.06
    Activations Density 0.021%

    No Known Activations