© 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. 58063
    Prev
    Next
    INDEX
    Explanations

    ent

    np_max-act · gemini-2.0-flash

    This neuron fires on subword tokens that are content-bearing stems (i.e. German noun/verb/adjective roots and derivational affixes) rather than on purely grammatical or function-word pieces.

    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
     alertDialog
    -0.06
     sine
    -0.06
     creator
    -0.06
     sean
    -0.06
    Save
    -0.06
     indexing
    -0.06
     Paula
    -0.06
     Arabia
    -0.06
     Reyes
    -0.06
    priv
    -0.06
    POSITIVE LOGITS
     Business
    0.06
     سرد
    0.06
    _produk
    0.06
    Nit
    0.06
    Cad
    0.06
     immobil
    0.06
    getFullYear
    0.06
    kowski
    0.06
    532
    0.06
    ει
    0.06
    Activations Density 0.059%

    No Known Activations