© 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. 44535
    Prev
    Next
    INDEX
    Explanations

    academic reference

    np_max-act · gemini-2.0-flash

    This neuron detects in‐text citation markers or reference tags (e.g. the bracketed author–year or numbered citations).

    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
     тогда
    -0.07
    だろう
    -0.07
     کوچ
    -0.06
     tangled
    -0.06
     düny
    -0.06
     imageView
    -0.06
    /helper
    -0.06
    .masksToBounds
    -0.06
    ียวก
    -0.06
     등
    -0.06
    POSITIVE LOGITS
     tomb
    0.06
     getInt
    0.06
     AW
    0.06
     Ти
    0.06
     gece
    0.06
     Indiana
    0.06
    >C
    0.06
    >G
    0.06
    ानद
    0.06
     painful
    0.06
    Activations Density 0.003%

    No Known Activations