© 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. 54332
    Prev
    Next
    INDEX
    Explanations

    informal online discussions

    np_max-act · gemini-2.0-flash

    The neuron is a detector for English gerund/participle forms (i.e. verb “-ing” endings).

    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
    ύ
    -0.06
    ."↵
    -0.06
    ,");↵
    -0.06
    .↵
    -0.06
     이것
    -0.06
     Succ
    -0.06
    Bl
    -0.06
     navy
    -0.06
     partic
    -0.05
     ΠΡ
    -0.05
    POSITIVE LOGITS
     since
    0.08
     поэтому
    0.07
    ораз
    0.07
     caching
    0.07
     offs
    0.07
     asserting
    0.07
     cuz
    0.07
     حافظ
    0.07
     upto
    0.07
     perché
    0.06
    Activations Density 0.304%

    No Known Activations