© 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. 54314
    Prev
    Next
    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash

    The neuron activates on decimal numbers in geographic descriptions—i.e. it picks up numeric tokens (like “3.19” or “3.07”) that often follow “in” in “is a … in X” statements.

    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
     Kelly
    -0.07
    Women
    -0.06
     wlan
    -0.06
    출장샵
    -0.06
    龙
    -0.06
    くと
    -0.06
     pes
    -0.06
    Month
    -0.06
    «
    -0.06
     Viewing
    -0.06
    POSITIVE LOGITS
     dough
    0.07
    -tone
    0.07
    Grace
    0.06
    Robot
    0.06
    urahan
    0.06
    itaire
    0.06
     Grace
    0.06
     türü
    0.06
    FFE
    0.06
    Preference
    0.06
    Activations Density 0.014%

    No Known Activations