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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 43605
    Prev
    Next
    INDEX
    Explanations

    coding exceptions and closing streams

    np_max-act · gemini-2.0-flash

    The neuron fires on code in “finally” blocks that closes or disposes of I/O resources (e.g. streams, sockets, readers).

    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
    말
    -0.07
     딸
    -0.07
    _Email
    -0.07
    .Search
    -0.07
    墨
    -0.06
    iff
    -0.06
    tries
    -0.06
    泊
    -0.06
     whisky
    -0.06
    .dao
    -0.06
    POSITIVE LOGITS
     чого
    0.07
     этот
    0.06
    �
    0.06
     vyp
    0.06
     yılında
    0.06
    χής
    0.06
     geldi
    0.06
    [attr
    0.06
    皆
    0.06
    .“
    0.06
    Activations Density 0.020%

    No Known Activations