© 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. 38177
    Prev
    Next
    INDEX
    Explanations

    Corp

    np_max-act · gemini-2.0-flash

    The neuron is detecting the slash‐delimited organization or department tags in email header addresses (e.g. “/Corp/”, “/ENRON/”, “/OU/”).

    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
     روست
    -0.07
     Terrain
    -0.07
    _aw
    -0.06
     Alone
    -0.06
    ;


↵
    -0.06
     Roku
    -0.06
     tým
    -0.06
    Blockly
    -0.06
     agrees
    -0.06
    Comparable
    -0.06
    POSITIVE LOGITS
    Analytics
    0.08
    ество
    0.07
     dif
    0.07
    Feb
    0.07
    ′
    0.07
    .UIManager
    0.07
    throw
    0.07
     ↔
    0.06
    وري
    0.06
     náklady
    0.06
    Activations Density 0.003%

    No Known Activations