© 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. 89760
    Prev
    Next
    INDEX
    Explanations

    announcements

    np_max-act · gemini-2.0-flash

    The neuron strongly activates on uppercase abbreviations and acronyms (e.g. ITS, EHRS, NYMEX, CUAlert), i.e. it detects all-caps organizational or system initials.

    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
     Combination
    -0.06
    iro
    -0.06
    ขนาด
    -0.06
    upil
    -0.06
     گیر
    -0.06
     jet
    -0.06
    longrightarrow
    -0.06
     Fir
    -0.06
     Compensation
    -0.06
    atches
    -0.06
    POSITIVE LOGITS
     Тому
    0.07
    σσότε
    0.07
     нату
    0.06
    (remove
    0.06
     Wishlist
    0.06
    �
    0.06
    -bordered
    0.06
     steward
    0.06
     راست
    0.06
    ‌
    0.06
    Activations Density 0.057%

    No Known Activations