© 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. 126346
    Prev
    Next
    INDEX
    Explanations

    Technical writing / code

    np_max-act · gemini-2.0-flash

    This neuron detects French statements about reading or seeing content (e.g., “j’ai lu… d’articles,” “vous m’aviez envoyé”).

    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
    _G
    -0.07
    ران
    -0.07
    Your
    -0.07
     Finished
    -0.07
    VBoxLayout
    -0.07
     surprise
    -0.07
     found
    -0.07
     phạt
    -0.06
     H
    -0.06
    しの
    -0.06
    POSITIVE LOGITS
     medic
    0.07
     unable
    0.07
     objectMapper
    0.07
     ERR
    0.06
     bek
    0.06
     brainstorm
    0.06
    PreparedStatement
    0.06
    (directory
    0.06
     클래스
    0.06
    OTTOM
    0.06
    Activations Density 0.000%

    No Known Activations