© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 8740
    Prev
    Next
    INDEX
    Explanations

    msgstr and msgid format

    np_max-act · gemini-2.0-flash

    The neuron fires on gettext translation markers (e.g. “msgid”/“msgstr” lines) in PO file content.

    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
    DU
    -0.07
    IV
    -0.06
     meiden
    -0.06
     MPU
    -0.06
    Commerce
    -0.06
    gain
    -0.06
    彼
    -0.06
     Claudia
    -0.06
    Marketing
    -0.06
     APP
    -0.06
    POSITIVE LOGITS
    や
    0.07
    Carrier
    0.07
     кал
    0.07
    ,更
    0.06
    /from
    0.06
    �
    0.06
     заклад
    0.06
    及
    0.06
    ѓ
    0.06
     зер
    0.06
    Activations Density 0.002%

    No Known Activations