© 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. 58816
    Prev
    Next
    INDEX
    Explanations

    OF

    np_max-act · gemini-2.0-flash

    The neuron fires on the uppercase “IN THE SUPREME COURT OF THE STATE OF …” header line, i.e. tokens marking a Supreme Court jurisdiction heading.

    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
    벌
    -0.06
    nad
    -0.06
    UIViewController
    -0.06
    >t
    -0.06
    asts
    -0.06
    _dice
    -0.06
    .hxx
    -0.06
     않은
    -0.06
    |m
    -0.06
    POSITIVE LOGITS
     proverb
    0.06
     suburb
    0.06
     unidades
    0.06
     paperwork
    0.06
     jus
    0.06
     wurden
    0.06
     scrut
    0.06
     alive
    0.06
     zvlá
    0.06
    .getFullYear
    0.06
    Activations Density 0.001%

    No Known Activations