© 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. 9301
    Prev
    Next
    INDEX
    Explanations

    mathematical notation

    np_max-act · gemini-2.0-flash

    This neuron detects LaTeX math‐mode commands and symbols (e.g. “\otimes”, “\times”, “\mathcal”, “\mathbb”, braces, backslashes) used for mathematical notation.

    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
     CONTRIBUTORS
    -0.08
    เลข
    -0.07
     прош
    -0.06
    idences
    -0.06
    เวลา
    -0.06
    REDIT
    -0.06
     표시
    -0.06
     قض
    -0.06
    credit
    -0.06
     pari
    -0.06
    POSITIVE LOGITS
     infringement
    0.07
    )..
    0.06
    'A
    0.06
     финансов
    0.06
    ‍
    0.06
     의해
    0.06
    FACE
    0.06
     instituted
    0.06
     dans
    0.05
     prez
    0.05
    Activations Density 0.006%

    No Known Activations