© 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. 109784
    Prev
    Next
    INDEX
    Explanations

    code syntax

    np_max-act · gemini-2.0-flash

    The neuron fires on numeric literal tokens (especially floating‐point numbers) in XML attribute conditions (e.g. version or condition values).

    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
     amp
    -0.06
     apart
    -0.06
    products
    -0.06
     अध
    -0.06
     explan
    -0.06
    .glob
    -0.06
     Dolphin
    -0.06
     uniqu
    -0.06
    лав
    -0.06
    .gc
    -0.06
    POSITIVE LOGITS
    SEM
    0.07
     continues
    0.06
    etypes
    0.06
    xE
    0.06
    ?,?,?,?,
    0.06
     제출
    0.06
    iej
    0.06
     ویژگی
    0.06
    ?,?,
    0.06
     mệnh
    0.06
    Activations Density 0.001%

    No Known Activations