© 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. 57504
    Prev
    Next
    INDEX
    Explanations

    Conditions and possibilities

    np_max-act · gemini-2.0-flash

    The neuron activates on references to academic or educational credentials, especially mentions of graduate-level studies.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    phrases related to inventions and mechanisms for waste disposal, specifically in the context of pet care.

    oai_token-act-pair · gpt-4o-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
    这一
    -0.07
     third
    -0.07
    itzer
    -0.06
     yarn
    -0.06
     pink
    -0.06
    auf
    -0.06
     Morse
    -0.06
    此
    -0.06
     evaluation
    -0.06
    قية
    -0.06
    POSITIVE LOGITS
     المغرب
    0.07
    .Contains
    0.07
     enthusi
    0.07
     indust
    0.06
    .monitor
    0.06
    ＼
    0.06
    _WE
    0.06
    dration
    0.06
    蜘蛛词
    0.06
    .getcwd
    0.06
    Activations Density 0.136%

    No Known Activations