© 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. 89338
    Prev
    Next
    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash

    This neuron detects the verb “aid” (as in “aid in …”), flagging instances where assistance or support is mentioned.

    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
    ΕΙΣ
    -0.06
    GRP
    -0.06
     places
    -0.06
     Marcel
    -0.06
     knot
    -0.06
     beep
    -0.06
    Shop
    -0.06
     Brut
    -0.06
    aptop
    -0.06
     Microsoft
    -0.06
    POSITIVE LOGITS
    .Endpoint
    0.07
    hub
    0.07
     aided
    0.07
    ينات
    0.07
    .heroku
    0.07
    (substr
    0.06
    .single
    0.06
    .slim
    0.06
    .WriteAllText
    0.06
     sunglasses
    0.06
    Activations Density 0.018%

    No Known Activations