© 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
    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. 7318
    Prev
    Next
    INDEX
    Explanations

    Scientific publications

    np_max-act · gemini-2.0-flash

    structures and relationships within mathematical equations or functions.

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

    This neuron is selectively detecting LaTeX‐style citation and reference delimiters—specifically square‐bracket and curly‐brace token sequences used around citations and bibliography macros.

    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
     facial
    -0.08
     zdję
    -0.08
    reviews
    -0.08
    drops
    -0.07
    orpion
    -0.07
     paintings
    -0.07
     Mor
    -0.07
     cocina
    -0.07
     neighbours
    -0.06
    dech
    -0.06
    POSITIVE LOGITS
     Pluto
    0.07
    ้จ
    0.07
    sgi
    0.07
    	extern
    0.06
    {}
    0.06
     '{}'
    0.06
    jadi
    0.06
    )?;↵↵
    0.06
    -issue
    0.06
     isim
    0.06
    Activations Density 0.002%

    No Known Activations