© 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. 124887
    Prev
    Next
    INDEX
    Explanations

    name

    np_max-act · gemini-2.0-flash

    keywords related to network operations and configurations in programming.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron activates on programming identifiers—especially CamelCase class, method, and parameter names in autogenerated API/client code.

    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
    thes
    -0.07
    Pdf
    -0.07
    jni
    -0.06
    ADD
    -0.06
    jabi
    -0.06
     Aires
    -0.06
    Fil
    -0.06
    arris
    -0.06
     dítě
    -0.06
     racism
    -0.06
    POSITIVE LOGITS
    进入
    0.08
     možné
    0.07
     stre
    0.07
    _force
    0.06
    :*
    0.06
     "*
    0.06
     هنگام
    0.06
     ارزش
    0.06
    %',↵
    0.06
    ーブ
    0.06
    Activations Density 0.008%

    No Known Activations