© 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. 56408
    Prev
    Next
    INDEX
    Explanations

    enth

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of the court’s circuit designation (e.g. “Tenth Circuit,” “10th Cir.”).

    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
    ucket
    -0.07
     solutions
    -0.07
     lol
    -0.07
     prendre
    -0.07
     Gaza
    -0.07
     acknowledgment
    -0.07
     Pak
    -0.07
    marshaller
    -0.07
     Hou
    -0.07
     ReadOnly
    -0.06
    POSITIVE LOGITS
    垂
    0.06
     공동
    0.06
     Dependencies
    0.06
    punkt
    0.06
    ATHER
    0.06
     взя
    0.06
    омина
    0.06
     meslek
    0.06
     casually
    0.06
     тщ
    0.05
    Activations Density 0.001%

    No Known Activations