© 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. 92283
    Prev
    Next
    INDEX
    Explanations

    EN

    np_max-act · gemini-2.0-flash

    The neuron fires on the “EN” token in HTML DOCTYPE public identifiers (e.g. the “//EN” language code in a DTD declaration).

    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
     }*/↵
    -0.06
    ches
    -0.06
    (snapshot
    -0.06
    repid
    -0.06
    แลนด
    -0.06
    acağını
    -0.06
    -times
    -0.06
    365
    -0.06
     hours
    -0.06
    QUIT
    -0.06
    POSITIVE LOGITS
    IDENT
    0.06
    -N
    0.06
    -ended
    0.06
     recursively
    0.06
     discovery
    0.06
     Ellen
    0.06
    .getLength
    0.06
     Regulatory
    0.06
     backgroundColor
    0.06
    Howard
    0.06
    Activations Density 0.000%

    No Known Activations