© 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
    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. 127052
    Prev
    Next
    INDEX
    Explanations

    bot

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of thrombotic processes or related terms (e.g., “thrombotic,” “thrombosis,” “thrombophilia”).

    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
     mereka
    -0.06
     mm
    -0.06
     Run
    -0.06
     Jam
    -0.06
    یره
    -0.06
     Freak
    -0.06
    lew
    -0.06
     Rain
    -0.06
     darf
    -0.06
    σουν
    -0.06
    POSITIVE LOGITS
    .POS
    0.08
    Obama
    0.08
     toolbox
    0.07
    groundColor
    0.07
     Plaint
    0.07
    (link
    0.07
     �
    0.07
     Postal
    0.07
    ixed
    0.07
    Tom
    0.07
    Activations Density 0.004%

    No Known Activations