© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 109230
    Prev
    Next
    INDEX
    Explanations

    table

    np_max-act · gemini-2.0-flash

    This neuron fires on SQL identifiers—things like table names, column names, and aliases (e.g. uppercase words with underscores).

    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
    plans
    -0.07
     TestData
    -0.06
     Halk
    -0.06
    hz
    -0.06
    ddf
    -0.06
    .getcwd
    -0.06
    र
    -0.06
    otional
    -0.06
    self
    -0.06
    ivě
    -0.06
    POSITIVE LOGITS
    -collection
    0.07
    _shop
    0.07
     architecture
    0.06
     есть
    0.06
     water
    0.06
     mothers
    0.06
    目标
    0.06
     섬
    0.06
     equ
    0.06
     features
    0.06
    Activations Density 0.046%

    No Known Activations