© 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. 91200
    Prev
    Next
    INDEX
    Explanations

    medical advice

    np_max-act · gemini-2.0-flash

    The neuron detects questions that ask which type of specialist to consult (e.g. “should I see an otologist or a dentist?”).

    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
    isiert
    -0.07
    eter
    -0.07
    aac
    -0.07
    ernaut
    -0.07
    標
    -0.07
    ΕΝ
    -0.06
    تح
    -0.06
    hydro
    -0.06
    Kit
    -0.06
    .startTime
    -0.06
    POSITIVE LOGITS
     تقد
    0.06
     mostra
    0.06
    kek
    0.06
     Stoke
    0.06
    驾
    0.06
    abancı
    0.06
    jde
    0.06
     admire
    0.06
     flawed
    0.06
    meeting
    0.06
    Activations Density 0.006%

    No Known Activations