© 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. 15-RESID-POST-AA
    11. 22571
    Prev
    Next
    INDEX
    Explanations

    supersymmetry

    np_max-act · gemini-2.0-flash

    mentions of supersymmetry or "super"-prefixed technical terms in physics contexts.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0

    The neuron detects tokens containing the "super-" morphological prefix and related concept tokens (i.e., mentions of super-related concepts in theoretical physics).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     и
    -0.07
    �
    -0.07
     larg
    -0.07
     не
    -0.07
    +N
    -0.06
    Been
    -0.06
    ุ่
    -0.06
    ignKey
    -0.06
    TexParameter
    -0.06
    straint
    -0.06
    POSITIVE LOGITS
     pretending
    0.08
     univerz
    0.07
    midd
    0.07
     dbus
    0.07
    _COMPLEX
    0.06
     hend
    0.06
    	rows
    0.06
     successor
    0.06
    Raises
    0.06
     DISCLAIMER
    0.06
    Activations Density 0.003%

    No Known Activations