© 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. 37906
    Prev
    Next
    INDEX
    Explanations

    academic publications

    np_max-act · gemini-2.0-flash

    The neuron detects bibliographic metadata blocks in academic or technical documents (author names, affiliations, publication dates/venues, and contact information).

    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
     pudding
    -0.07
    .RequestBody
    -0.06
    router
    -0.06
    鬼
    -0.06
     payment
    -0.06
    IconModule
    -0.06
     pz
    -0.06
     pt
    -0.06
    .FindGameObjectWithTag
    -0.06
     갈
    -0.06
    POSITIVE LOGITS
     تحت
    0.07
    (add
    0.07
    юн
    0.06
     meiner
    0.06
     الم
    0.06
     lokal
    0.06
    0.06
     pageInfo
    0.06
    	open
    0.06
     Austria
    0.06
    Activations Density 0.012%

    No Known Activations