© 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. 91548
    Prev
    Next
    INDEX
    Explanations

    n

    np_max-act · gemini-2.0-flash

    The neuron activates on C/C++ preprocessor include statements, particularly the header‐file path tokens (e.g. the quoted file names and “.h” components).

    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
    Yet
    -0.07
     Copies
    -0.07
    utterstock
    -0.07
    ."
    -0.07
     posted
    -0.06
     أد
    -0.06
     classifiers
    -0.06
    already
    -0.06
    евые
    -0.06
    provided
    -0.06
    POSITIVE LOGITS
    _Two
    0.06
    Pok
    0.06
     OleDb
    0.06
    TabControl
    0.06
    baz
    0.06
    (lock
    0.06
     ตำบล
    0.06
     ваш
    0.06
     необ
    0.06
    .crm
    0.06
    Activations Density 0.014%

    No Known Activations