© 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
    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. 44467
    Prev
    Next
    INDEX
    Explanations

    raction

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on specialized scientific or technical jargon—particularly multiword, hyphenated, or domain‐specific terms (e.g. “solid–gas interface,” “P-wave,” “fluorescein dye,” “spray-drying”).

    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
     prosecute
    -0.07
     Toolbox
    -0.06
    718
    -0.06
    ee
    -0.06
    (obj
    -0.06
    _fit
    -0.06
     Ludwig
    -0.06
    peak
    -0.06
     海
    -0.06
     Synthetic
    -0.06
    POSITIVE LOGITS
    ком
    0.08
     vagina
    0.06
    DevExpress
    0.06
     이전
    0.06
    /facebook
    0.06
     consequently
    0.06
    :href
    0.06
    .setIcon
    0.06
    operator
    0.06
     QLD
    0.06
    Activations Density 0.215%

    No Known Activations