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

    Neuronpedia

    Jacobian LensNEW
    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. 57059
    Prev
    Next
    INDEX
    Explanations

    headaches

    np_max-act · gemini-2.0-flash

    The neuron fires on words naming or describing unpleasant physical symptoms (like diarrhea, loose stools, headaches, dehydration, fatigue, etc.).

    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
    	idx
    -0.07
    aptcha
    -0.07
     bourgeois
    -0.06
     peso
    -0.06
    厚
    -0.06
     bước
    -0.06
     PendingIntent
    -0.06
    .BadRequest
    -0.06
    fidf
    -0.06
    Attach
    -0.06
    POSITIVE LOGITS
     sins
    0.07
     Mae
    0.07
     امر
    0.06
     اجتماع
    0.06
     ActionTypes
    0.06
    рол
    0.06
    culator
    0.06
     Compiler
    0.06
    icester
    0.06
    ा.
    0.06
    Activations Density 0.003%

    No Known Activations