© 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. 55970
    Prev
    Next
    INDEX
    Explanations

    {

    np_max-act · gemini-2.0-flash

    The neuron detects floating‐point numeric literals (decimal constants) embedded in source 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
     сем
    -0.06
     THPT
    -0.06
     Nhĩ
    -0.06
     çoğ
    -0.06
    θενής
    -0.06
    [@"
    -0.06
    jec
    -0.06
    uyễn
    -0.06
    .borrow
    -0.06
    rání
    -0.06
    POSITIVE LOGITS
    easy
    0.08
     collectively
    0.07
     accessing
    0.07
     Zhu
    0.07
     announces
    0.07
     effectively
    0.06
    department
    0.06
     leftover
    0.06
     adjusting
    0.06
     demanding
    0.06
    Activations Density 0.003%

    No Known Activations