© 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. 57806
    Prev
    Next
    INDEX
    Explanations

    white

    np_max-act · gemini-2.0-flash

    The neuron activates primarily on occurrences of the word “white.”

    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
    .getM
    -0.07
    .getItemId
    -0.07
     mam
    -0.06
    CCR
    -0.06
     Mandal
    -0.06
    {j
    -0.06
    jd
    -0.06
    .method
    -0.06
     Manor
    -0.06
    .kr
    -0.06
    POSITIVE LOGITS
     White
    0.16
    White
    0.15
     white
    0.14
    white
    0.14
    白
    0.12
     WHITE
    0.12
     Whites
    0.11
    -white
    0.11
     白
    0.11
    WHITE
    0.10
    Activations Density 0.021%

    No Known Activations