© 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. 73849
    Prev
    Next
    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    The neuron flags pieces of a Twig/Symfony template (e.g. block names, translation keys, `fos_user_content`, `trans` calls), i.e. template‐level markup and translation/filter tokens.

    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
    .dst
    -0.07
    (Map
    -0.07
    pickle
    -0.06
    .keywords
    -0.06
     tracking
    -0.06
    ()?>
    -0.06
    .TextInput
    -0.06
    行动
    -0.06
     Tracking
    -0.06
    .SERVER
    -0.06
    POSITIVE LOGITS
     complain
    0.08
    الع
    0.06
     interconnected
    0.06
    0.06
    occupied
    0.06
    чают
    0.06
    Prior
    0.06
     Nome
    0.06
     Scarborough
    0.06
     yn
    0.06
    Activations Density 0.267%

    No Known Activations