© 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. 124811
    Prev
    Next
    INDEX
    Explanations

    Medical/research contexts

    np_max-act · gemini-2.0-flash

    The neuron detects words naming human actors or roles (e.g. citizen, scientist, nurse, paramedic, anesthesiologist, trainee).

    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
    یره
    -0.08
     destroyed
    -0.07
     temperatures
    -0.07
    ckpt
    -0.07
     Mil
    -0.07
    .after
    -0.06
     terms
    -0.06
     obligations
    -0.06
    eda
    -0.06
    -negative
    -0.06
    POSITIVE LOGITS
     رایگان
    0.07
    _extract
    0.06
    чай
    0.06
    (io
    0.06
    reports
    0.06
    Ngoài
    0.06
     الزر
    0.06
    _cliente
    0.06
     insist
    0.06
     helfen
    0.06
    Activations Density 0.020%

    No Known Activations