© 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. 57774
    Prev
    Next
    INDEX
    Explanations

    en

    np_max-act · gemini-2.0-flash

    This neuron detects occurrences of the HTML lang attribute set to English (e.g. “en,” “en-US,” “en-us”).

    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
    Coding
    -0.07
    umps
    -0.07
    írk
    -0.07
     اض
    -0.07
     Faces
    -0.07
    Як
    -0.07
    Benchmark
    -0.07
    .getData
    -0.06
    ProgressBar
    -0.06
    esi
    -0.06
    POSITIVE LOGITS
    /common
    0.06
     concerns
    0.06
    rice
    0.06
     Мин
    0.06
     prevalent
    0.06
     Ekon
    0.06
    _rel
    0.06
     considered
    0.06
     conventional
    0.06
     SOME
    0.05
    Activations Density 0.001%

    No Known Activations