© 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. 126932
    Prev
    Next
    INDEX
    Explanations

    ED

    np_max-act · gemini-2.0-flash

    The neuron strongly activates on the “ED” fragment in the uppercase heading “UNITED STATES,” effectively detecting the “UNITED STATES” label in document headings.

    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
    ,index
    -0.07
    Decor
    -0.07
    _Box
    -0.06
    Dam
    -0.06
     знов
    -0.06
    aaaaaaaa
    -0.06
    —for
    -0.06
    ioms
    -0.06
    orsk
    -0.06
     sideways
    -0.06
    POSITIVE LOGITS
     United
    0.17
     UNITED
    0.13
    United
    0.12
     united
    0.08
     unite
    0.08
    .Positive
    0.07
     liên
    0.07
     married
    0.07
    FT
    0.07
    UNIT
    0.07
    Activations Density 0.009%

    No Known Activations