© 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. 43157
    Prev
    Next
    INDEX
    Explanations

    applied force

    np_max-act · gemini-2.0-flash

    This neuron responds to technical terms describing physical or mechanical properties and actions—especially stress, load, and related material-property variations.

    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
     conduc
    -0.08
    elor
    -0.07
    _val
    -0.07
    IW
    -0.06
    äll
    -0.06
    уже
    -0.06
    mandatory
    -0.06
    naments
    -0.06
    -backed
    -0.06
    Archivo
    -0.06
    POSITIVE LOGITS
    .Random
    0.07
     Up
    0.06
     Executive
    0.06
     аром
    0.06
    -bot
    0.06
    ．
    0.06
     Vanity
    0.06
     Dance
    0.06
     Autism
    0.06
     Stake
    0.06
    Activations Density 0.088%

    No Known Activations