© 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. 74806
    Prev
    Next
    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on numeric literals (especially decimal numbers) in SQL type definitions.

    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
    File
    -0.07
     Lopez
    -0.06
    -by
    -0.06
     �
    -0.06
    局
    -0.06
     submits
    -0.06
    944
    -0.06
     美国
    -0.06
    TEAM
    -0.06
     Smy
    -0.06
    POSITIVE LOGITS
     guardians
    0.07
    _storage
    0.07
    《
    0.07
    _mid
    0.07
     handic
    0.06
     práv
    0.06
     perpetual
    0.06
     раді
    0.06
     gentlemen
    0.06
    _USB
    0.06
    Activations Density 0.004%

    No Known Activations