© 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. 44597
    Prev
    Next
    INDEX
    Explanations

    changes

    np_max-act · gemini-2.0-flash

    This neuron detects the special end‐of‐header marker token (e.g., “<|end_header_id|>”).

    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
    تمر
    -0.07
     Sheriff
    -0.06
    trecht
    -0.06
    �
    -0.06
    ملكة
    -0.06
    어
    -0.06
     layui
    -0.06
    관리자
    -0.06
    ecký
    -0.06
     CONSEQUENTIAL
    -0.06
    POSITIVE LOGITS
    Construct
    0.06
     Levin
    0.06
     undermined
    0.06
     deficit
    0.06
     extended
    0.06
     petition
    0.06
     classification
    0.06
    ']}↵
    0.06
    (',')↵
    0.06
     raw
    0.06
    Activations Density 0.009%

    No Known Activations