© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 125111
    Prev
    Next
    INDEX
    Explanations

    update

    np_max-act · gemini-2.0-flash

    interfaces that define CRUD operations for generic data management in a programming context.

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

    This neuron detects occurrences of “update” (especially in the context of HTTP PUT/update endpoints) in controller 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
     SizedBox
    -0.06
     gospel
    -0.06
     dbs
    -0.06
    ventions
    -0.06
    шибка
    -0.06
     Lev
    -0.06
    "];↵
    -0.06
     Callback
    -0.06
    _Show
    -0.06
    okes
    -0.05
    POSITIVE LOGITS
     underground
    0.07
     submar
    0.07
     slowed
    0.07
    -signed
    0.07
    .update
    0.07
    ablo
    0.06
     swinger
    0.06
    /K
    0.06
    ้าน
    0.06
    updating
    0.06
    Activations Density 0.007%

    No Known Activations