© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 38505
    Prev
    Next
    INDEX
    Explanations

    inches

    np_max-act · gemini-2.0-flash

    discussions related to the mechanics and techniques of baseball pitching.

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

    The neuron fires on numeric measurements and dimension tokens (e.g. “1 / 4-inch thick,” “one foot deep,” etc.).

    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
     yaw
    -0.07
    ():
↵
    -0.07
    **
↵
    -0.06
     hã
    -0.06
    kenin
    -0.06
     dims
    -0.06
    .Arg
    -0.06
    ,n
    -0.06
     отк
    -0.06
    лугов
    -0.06
    POSITIVE LOGITS
    \-
    0.07
     آمریک
    0.07
     scare
    0.07
    Προ
    0.06
     embarrassing
    0.06
    bourne
    0.06
    .IsChecked
    0.06
     homeschool
    0.06
    ountry
    0.06
     prt
    0.06
    Activations Density 0.081%

    No Known Activations