© 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. 74714
    Prev
    Next
    INDEX
    Explanations

    von Neumann

    np_max-act · gemini-2.0-flash

    the contributions and concepts related to John von Neumann's work in mathematics and computer science.

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

    This neuron activates on occurrences of the name “Neumann” (especially in “von Neumann”), identifying mentions of John von Neumann or the von Neumann architecture.

    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
    По
    -0.07
     remarks
    -0.07
    Clark
    -0.07
    children
    -0.06
    idge
    -0.06
    -ps
    -0.06
     rab
    -0.06
     flourishing
    -0.06
     fears
    -0.06
    Ly
    -0.06
    POSITIVE LOGITS
    特
    0.07
     �
    0.07
    _TIMESTAMP
    0.07
    _mot
    0.06
     detach
    0.06
    JOIN
    0.06
     secara
    0.06
     떨어
    0.06
    BOOT
    0.06
    _sell
    0.06
    Activations Density 0.000%

    No Known Activations