Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 22393
    Prev
    Next
    INDEX
    Explanations

    ResultSet

    np_max-act · gemini-2.0-flash

    Java code related to database operations and error handling.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The main thing this neuron does is find Java JDBC database‐access code.

    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
     thuyết
    -0.08
    ुज
    -0.07
     sodium
    -0.07
     statusBar
    -0.06
    _FN
    -0.06
     scaleFactor
    -0.06
    hone
    -0.06
     cab
    -0.06
    ='../
    -0.06
     Potential
    -0.06
    POSITIVE LOGITS
     ResultSet
    0.08
    _Red
    0.06
     resultSet
    0.06
     ̄ ̄ ̄ ̄
    0.06
     Luft
    0.06
    mouse
    0.06
     PCS
    0.06
     عالم
    0.06
     Rew
    0.06
    java
    0.06
    Activations Density 0.003%

    No Known Activations