© 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. 92461
    Prev
    Next
    INDEX
    Explanations

    SQLAlchemy

    np_max-act · gemini-2.0-flash

    The neuron consistently activates on occurrences of “SQLAlchemy,” i.e. it flags mentions of the SQLAlchemy database/ORM library.

    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
    .BorderColor
    -0.07
     týden
    -0.07
    .stroke
    -0.07
     Manuel
    -0.07
    ใส
    -0.06
     púb
    -0.06
     Fotos
    -0.06
    .await
    -0.06
    IOR
    -0.06
    .cols
    -0.06
    POSITIVE LOGITS
     SQLAlchemy
    0.09
    alignment
    0.08
     brain
    0.07
    (sum
    0.07
     Erk
    0.06
     departing
    0.06
    -through
    0.06
    statements
    0.06
    token
    0.06
    cycles
    0.06
    Activations Density 0.000%

    No Known Activations