© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 6401
    Prev
    Next
    INDEX
    Explanations

    PhD

    np_max-act · gemini-2.0-flash

    technical terms and concepts related to theoretical mathematics.

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

    This neuron detects mentions of academic credentials and scholarly affiliations—e.g. degree titles, thesis references, and university names.

    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
    Interest
    -0.06
     stock
    -0.06
    Dead
    -0.06
    ضافة
    -0.06
    _peng
    -0.06
     coercion
    -0.06
    Scripts
    -0.06
     hic
    -0.06
    _mesh
    -0.06
     equitable
    -0.06
    POSITIVE LOGITS
     Lower
    0.07
    ulen
    0.06
    dera
    0.06
     ヾ
    0.06
     langs
    0.06
     aynı
    0.06
     Silent
    0.06
     ┃
    0.06
     #@
    0.06
    ắn
    0.06
    Activations Density 0.011%

    No Known Activations