© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 109279
    Prev
    Next
    INDEX
    Explanations

    np

    np_max-act · gemini-2.0-flash

    methods of comparing numerical data, particularly embeddings in machine learning.

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

    The neuron fires on mentions of NumPy array‐ or matrix‐processing function calls (e.g. np.histogram2d, np.rot90, np.flipud, np.ma.masked_where).

    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
    νομα
    -0.07
     Bath
    -0.07
    STER
    -0.07
     broken
    -0.07
     şah
    -0.07
    shield
    -0.07
    dd
    -0.07
    _TRA
    -0.06
    atform
    -0.06
    ature
    -0.06
    POSITIVE LOGITS
    :indexPath
    0.07
    の
    0.07
     �
    0.07
    implicitly
    0.07
    ographed
    0.07
     농
    0.06
     LN
    0.06
     zprac
    0.06
    竞
    0.06
    相当
    0.06
    Activations Density 0.010%

    No Known Activations