© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 7739
    Prev
    Next
    INDEX
    Explanations

    Legal document punctuation/numbers

    np_max-act · gemini-2.0-flash

    The neuron activates on tokens that are part of numbered legal citations—e.g. statute and rule numbers, case‐report volume and page numbers, and other numeric reference markers.

    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
    q
    -0.07
     Cara
    -0.07
    .proc
    -0.06
     Kramer
    -0.06
    adní
    -0.06
    روس
    -0.06
    _IND
    -0.06
     randomNumber
    -0.06
    Js
    -0.06
    commercial
    -0.06
    POSITIVE LOGITS
    .Diagnostics
    0.06
     Edited
    0.06
     puzzles
    0.06
     نگ
    0.06
    lif
    0.06
     Moder
    0.06
     те
    0.06
     bolt
    0.06
    games
    0.06
    ٨
    0.06
    Activations Density 0.002%

    No Known Activations