© 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. 38097
    Prev
    Next
    INDEX
    Explanations

    gene

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of gene‐delivery and gene‐therapy contexts (e.g. “gene,” “delivery,” “transfection,” “therapy,” “vector,” 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
    han
    -0.07
    amac
    -0.07
    inem
    -0.07
    ithub
    -0.07
    Real
    -0.07
    emand
    -0.06
    .large
    -0.06
    negative
    -0.06
    linger
    -0.06
     Fernandez
    -0.06
    POSITIVE LOGITS
     assass
    0.07
     gases
    0.07
     Міністер
    0.06
    �
    0.06
     easy
    0.06
     stopped
    0.06
     CMD
    0.06
     Mae
    0.06
     shake
    0.06
     Ass
    0.06
    Activations Density 0.009%

    No Known Activations