© 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. 38398
    Prev
    Next
    INDEX
    Explanations

    hormones and contraception

    np_max-act · gemini-2.0-flash

    The neuron sharply activates on pharmaceutical progestin names (e.g. levonorgestrel, norethisterone) in the text.

    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
     підприємств
    -0.07
    Look
    -0.06
     Biggest
    -0.06
     Registro
    -0.06
     게임
    -0.06
     کامپی
    -0.06
     pathogens
    -0.06
    izyon
    -0.06
    Share
    -0.06
    iped
    -0.06
    POSITIVE LOGITS
     supplied
    0.08
    FINITE
    0.06
     separate
    0.06
    <TSource
    0.06
    monic
    0.06
    29
    0.06
    supply
    0.06
    ψει
    0.06
     ($
    0.06
    ofilm
    0.06
    Activations Density 0.004%

    No Known Activations