© 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. 55419
    Prev
    Next
    INDEX
    Explanations

    collections

    np_max-act · gemini-2.0-flash

    The neuron fires on references to Python’s `collections` module (e.g. when importing or using `Counter`, `OrderedDict`, `defaultdict`, `deque`, etc.).

    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
     Hyp
    -0.06
     Indust
    -0.06
    Sir
    -0.06
     Sphere
    -0.06
     等
    -0.06
    Ign
    -0.06
    posable
    -0.06
    multip
    -0.06
    _seat
    -0.06
     lst
    -0.06
    POSITIVE LOGITS
     Podle
    0.07
    しまった
    0.07
    **************
    0.07
     orderId
    0.06
     adorned
    0.06
     Originally
    0.06
    ケース
    0.06
     toppings
    0.06
    _FIRE
    0.06
     NUnit
    0.06
    Activations Density 0.001%

    No Known Activations