© 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. 44473
    Prev
    Next
    INDEX
    Explanations

    set

    np_max-act · gemini-2.0-flash

    This neuron detects occurrences of “set” method calls (i.e., tokens beginning with “set” in method invocation names).

    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
    (tx
    -0.07
    /arch
    -0.07
     Astr
    -0.07
     inex
    -0.07
    Unix
    -0.06
    .pr
    -0.06
     �
    -0.06
     Away
    -0.06
     ciz
    -0.06
    싱
    -0.06
    POSITIVE LOGITS
    .set
    0.09
     alternative
    0.08
     etme
    0.07
    设置
    0.07
     станет
    0.06
    TreeNode
    0.06
    \Response
    0.06
    .stringify
    0.06
     Xxx
    0.06
    าชน
    0.06
    Activations Density 0.013%

    No Known Activations