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

    Neuronpedia

    Jacobian LensNEW
    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. 38848
    Prev
    Next
    INDEX
    Explanations

    AS

    np_max-act · gemini-2.0-flash

    This neuron detects Common Table Expression declarations in T-SQL, i.e. the “WITH … AS” pattern.

    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
    >{
    -0.07
    ingt
    -0.06
    _play
    -0.06
    QUENCE
    -0.06
    لت
    -0.06
     reaction
    -0.06
     launch
    -0.06
    효
    -0.06
    ystate
    -0.06
    component
    -0.06
    POSITIVE LOGITS
    .entrySet
    0.07
     paramString
    0.07
     incentives
    0.07
     सर
    0.07
     ↓
    0.07
    ви
    0.06
     公司
    0.06
     바람
    0.06
     thinking
    0.06
    CGPoint
    0.06
    Activations Density 0.002%

    No Known Activations