© 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 EvalsExportsAPI 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. 38745
    Prev
    Next
    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash

    This neuron fires on the court‐header metadata listing the judges (e.g. “Chief Judge,” “Circuit Judge,” and judge names) in appellate opinions.

    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
    !='
    -0.07
    tube
    -0.06
     san
    -0.06
    他
    -0.06
    (at
    -0.06
     vk
    -0.06
     actively
    -0.06
    Descripcion
    -0.06
    िसस
    -0.06
     SCREEN
    -0.06
    POSITIVE LOGITS
     Bengals
    0.07
    교
    0.06
     Exceptions
    0.06
     Wifi
    0.06
     Sting
    0.06
     haul
    0.06
    acím
    0.06
    ibilities
    0.06
    ��
    0.06
    UTC
    0.06
    Activations Density 0.010%

    No Known Activations