© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 59346
    Prev
    Next
    INDEX
    Explanations

    Cho

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of small populated places and their names (e.g., towns, villages, settlements, communities).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    Imports
    -0.07
    STRACT
    -0.07
     bc
    -0.06
     Compile
    -0.06
    Courses
    -0.06
    Cou
    -0.06
    ritte
    -0.06
    Define
    -0.06
    	Output
    -0.06
    :bold
    -0.06
    POSITIVE LOGITS
    (len
    0.07
    قية
    0.06
    git
    0.06
    /q
    0.06
    _icall
    0.06
     `}↵
    0.06
     الحرب
    0.06
    南
    0.06
    -screen
    0.06
    twig
    0.06
    Activations Density 0.072%

    No Known Activations