© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 56065
    Prev
    Next
    INDEX
    Explanations

    defer

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of postponement or delay—i.e. contexts where something is being deferred.

    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
     tolik
    -0.07
     лит
    -0.07
     زیست
    -0.06
     lawsuit
    -0.06
    面积
    -0.06
     wereld
    -0.06
     الجز
    -0.06
     náměstí
    -0.06
     kitap
    -0.06
     کامپی
    -0.06
    POSITIVE LOGITS
     deferred
    0.13
     Deferred
    0.12
    .defer
    0.10
     defer
    0.10
    Deferred
    0.09
     postponed
    0.09
    .Dep
    0.08
    ;border
    0.07
    φέ
    0.07
    defer
    0.07
    Activations Density 0.002%

    No Known Activations