© 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. 59003
    Prev
    Next
    INDEX
    Explanations

    legal citations

    np_max-act · gemini-2.0-flash

    This neuron detects legal‐document reference markers—things like paragraph symbols (¶), section or “Facts” labels, party abbreviations (e.g. “Def.’s”), and other in-text citation cues.

    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
     Currently
    -0.07
    	ad
    -0.07
    oucí
    -0.07
    ่าน
    -0.06
    _sender
    -0.06
     attendees
    -0.06
    Tony
    -0.06
     mad
    -0.06
    /M
    -0.06
    lač
    -0.06
    POSITIVE LOGITS
     Truck
    0.08
     paw
    0.07
    pliers
    0.07
    _VARS
    0.07
     swirl
    0.06
    (MouseEvent
    0.06
     USSR
    0.06
    овар
    0.06
    plier
    0.06
     которых
    0.06
    Activations Density 0.003%

    No Known Activations