© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 68526
    Prev
    Next
    INDEX
    Explanations

    infinite

    np_max-act · gemini-2.0-flash

    code snippets related to integrating machine learning models and handling user input in Python scripts.

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

    This neuron responds to tokens that signal an infinite loop or loop‐control construct in code (e.g. “while True:” and related punctuation).

    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
     switches
    -0.07
     fields
    -0.07
    oxel
    -0.07
     усе
    -0.07
     interle
    -0.07
     markers
    -0.06
     refuge
    -0.06
    ocs
    -0.06
     deposits
    -0.06
     proxy
    -0.06
    POSITIVE LOGITS
     جم
    0.07
    航空
    0.06
     Matches
    0.06
     autistic
    0.06
    Apellido
    0.06
    _uri
    0.06
    ordum
    0.06
     تص
    0.06
    刀
    0.06
    疆
    0.06
    Activations Density 0.010%

    No Known Activations