© 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 EvalsExportsinterp-engineNEWAPI 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. 57549
    Prev
    Next
    INDEX
    Explanations

    racism

    np_max-act · gemini-2.0-flash

    This neuron detects explicitly racist language and slurs.

    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
     कब
    -0.07
    \Field
    -0.07
    =query
    -0.06
     maintenant
    -0.06
     �
    -0.06
     Cinder
    -0.06
     Dragon
    -0.06
     GPA
    -0.06
     //'
    -0.06
    PageRoute
    -0.06
    POSITIVE LOGITS
     whatsoever
    0.06
    0.06
    silent
    0.06
    sup
    0.06
     occurrences
    0.06
    .Pages
    0.06
    -enh
    0.06
    Sets
    0.06
     dangerously
    0.06
    0.06
    Activations Density 0.015%

    No Known Activations