© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 7729
    Prev
    Next
    INDEX
    Explanations

    >

    np_max-act · gemini-2.0-flash

    resources and UI elements related to app settings and dialogs.

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

    The neuron detects XML element openings (i.e. the “<tag” and “>” markers and element names) in Android resource files.

    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
    ‪
    -0.07
    .savefig
    -0.06
     کوچ
    -0.06
    Escape
    -0.06
    ,request
    -0.06
     όπως
    -0.06
     '^
    -0.06
     typealias
    -0.06
    License
    -0.06
    TCP
    -0.06
    POSITIVE LOGITS
     unus
    0.07
     steril
    0.07
     الج
    0.07
     scient
    0.06
    เล
    0.06
     BATCH
    0.06
     disg
    0.06
     Allows
    0.06
     phiên
    0.06
     Lotus
    0.06
    Activations Density 0.002%

    No Known Activations