© 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. 68460
    Prev
    Next
    INDEX
    Explanations

    City

    np_max-act · gemini-2.0-flash

    legal terminology related to court cases and judgments.

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

    The neuron is tuned to spot the multi‐word location “New York City.”

    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
    شر
    -0.06
    _thumbnail
    -0.06
    Sz
    -0.06
    _CONN
    -0.06
    Safe
    -0.06
     الض
    -0.06
    bson
    -0.06
     Trad
    -0.06
     temple
    -0.06
    Hom
    -0.06
    POSITIVE LOGITS
     {"
    0.07
     eliminates
    0.07
     Active
    0.07
     başarı
    0.07
     retire
    0.07
    hoe
    0.06
     incompetent
    0.06
     créd
    0.06
    ={"
    0.06
    <Response
    0.06
    Activations Density 0.007%

    No Known Activations