© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 6445
    Prev
    Next
    INDEX
    Explanations

    by

    np_max-act · gemini-2.0-flash

    This neuron detects the “Dismissed by … unpublished per curiam opinion” line in these court‐opinion headers.

    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
    solete
    -0.07
     Eins
    -0.06
     هدف
    -0.06
    ูกค
    -0.06
     پایه
    -0.06
    getMock
    -0.06
     AOL
    -0.06
    上げ
    -0.06
    rier
    -0.06
    Spaces
    -0.06
    POSITIVE LOGITS
     Bollywood
    0.06
     resembling
    0.06
    ней
    0.06
     Athletics
    0.06
    _BS
    0.06
     台
    0.06
     指
    0.06
     điện
    0.06
     Magical
    0.06
     abrir
    0.06
    Activations Density 0.001%

    No Known Activations