© 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. 43142
    Prev
    Next
    INDEX
    Explanations

    oscopic

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of laparoscopic procedures (tokens like “lap,” “aroscopic,” “oscopic,” etc., in words such as “laparoscopic” or “laparoscopy”).

    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
     Yad
    -0.07
     Chat
    -0.06
     disgusted
    -0.06
    Ul
    -0.06
     прот
    -0.06
    aja
    -0.06
     aire
    -0.06
    _intersect
    -0.06
     chat
    -0.06
    .T
    -0.06
    POSITIVE LOGITS
    سه
    0.07
    werk
    0.07
    _classes
    0.07
     victorious
    0.06
    's
    0.06
    анс
    0.06
    ه
    0.06
    ング
    0.06
    kok
    0.06
     Satoshi
    0.06
    Activations Density 0.004%

    No Known Activations